© 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. 2518
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to controversial topics and events

    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
    481
    +0.12
    0.6%
    712
    +0.11
    0.5%
    567
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.07
    288
    +0.11
    0.07
    459
    +0.10
    0.05
    Negative Logits
    ãģĦ
    -0.70
    abella
    -0.70
    »Ĵ
    -0.69
    ãĤ¨ãĥ«
    -0.65
     pregnancies
    -0.64
    eus
    -0.62
    ãĥ¯ãĥ³
    -0.62
    ousands
    -0.62
    omo
    -0.61
    åŃIJ
    -0.60
    POSITIVE LOGITS
     unto
    0.96
     devoid
    0.90
     akin
    0.89
     worthy
    0.85
     affair
    0.81
     nonetheless
    0.79
     unlike
    0.77
     rather
    0.77
     deserving
    0.76
    ifier
    0.74
    Activations Density 0.331%

    No Known Activations