© 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 EvalsExportsAPI 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. 12517
    Prev
    Next
    INDEX
    Explanations

    events, discussions, and statements related to political and social issues

    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
    447
    +0.16
    0.7%
    305
    +0.10
    0.5%
    760
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    115
    +0.16
    0.06
    305
    +0.10
    0.05
    693
    +0.10
    0.05
    Negative Logits
     compositions
    -0.65
     mete
    -0.63
     cop
    -0.62
     thy
    -0.60
    Owner
    -0.57
     birth
    -0.57
    omy
    -0.56
     prev
    -0.55
     proven
    -0.55
    ographic
    -0.54
    POSITIVE LOGITS
     yesterday
    0.93
    posium
    0.91
     convened
    0.89
     held
    0.82
     Thursday
    0.82
     chaired
    0.79
     unveiling
    0.79
     hosted
    0.79
    clave
    0.78
     attendees
    0.77
    Activations Density 0.215%

    No Known Activations