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 6144
    5. 8-RES_FS6144-JB
    6. 4517
    Prev
    Next
    INDEX
    Explanations

    time-related information and schedules

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    709
    +0.11
    0.5%
    361
    +0.10
    0.5%
    223
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.04
    220
    +0.10
    0.03
    127
    +0.09
    0.03
    Negative Logits
     exha
    -0.71
     reluct
    -0.67
     suscept
    -0.67
    ocene
    -0.66
    olson
    -0.65
    estine
    -0.64
    cube
    -0.62
     disadvant
    -0.61
    llular
    -0.61
     unaff
    -0.61
    POSITIVE LOGITS
    00
    1.02
    01
    0.83
    009
    0.82
    raction
    0.79
    arth
    0.78
    ors
    0.77
    003
    0.77
    30
    0.77
    004
    0.75
    50
    0.75
    Activations Density 0.245%

    No Known Activations