Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 312
    Prev
    Next
    INDEX
    Explanations

    words related to coding, programming, and technology

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    578
    +0.13
    0.6%
    159
    +0.11
    0.5%
    166
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.13
    0.09
    232
    +0.11
    0.09
    326
    +0.09
    0.12
    Negative Logits
    kson
    -0.85
    assetsadobe
    -0.80
    getic
    -0.78
     Pru
    -0.71
    à¨
    -0.69
    sburgh
    -0.69
    auna
    -0.65
    iage
    -0.65
    éĹĺ
    -0.64
    cki
    -0.63
    POSITIVE LOGITS
    peria
    1.16
    avier
    1.14
    aminer
    1.07
    posed
    1.01
    yz
    0.99
    cellent
    0.97
     Machina
    0.94
    actly
    0.92
    cellence
    0.86
    press
    0.84
    Activations Density 3.628%

    No Known Activations