© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 20883
    Prev
    Next
    INDEX
    Explanations

    - words related to fraudulent activities, financial market activities, and Bitcoin investment. - terms related to political conflicts and insults. - opinions and concerns about political figures and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    311
    +0.12
    0.5%
    314
    +0.11
    0.5%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.12
    0.02
    128
    +0.11
    0.03
    578
    +0.11
    0.02
    Negative Logits
     Boone
    -0.72
     clipboard
    -0.69
     Lizard
    -0.68
     Bots
    -0.67
     Leopard
    -0.66
     Clash
    -0.64
     messenger
    -0.63
     Haku
    -0.63
     paraly
    -0.62
     execution
    -0.62
    POSITIVE LOGITS
    urther
    1.44
    eatured
    1.41
    rozen
    1.39
    actory
    1.35
    amiliar
    1.33
    avorable
    1.32
    avour
    1.32
    ortunate
    1.31
    ruits
    1.31
    ocusing
    1.30
    Activations Density 0.028%

    No Known Activations