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 3072
    5. 8-RES_FS3072-JB
    6. 1177
    Prev
    Next
    INDEX
    Explanations

    game-related instructions and information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    373
    +0.12
    0.6%
    329
    +0.09
    0.4%
    566
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.09
    227
    +0.09
    0.04
    570
    +0.08
    0.01
    Negative Logits
    lihood
    -0.61
     Tuls
    -0.57
     Sven
    -0.57
     Pruitt
    -0.54
     Ballard
    -0.54
     Kush
    -0.53
     Greenpeace
    -0.53
    OSH
    -0.52
     Nun
    -0.52
     Roose
    -0.51
    POSITIVE LOGITS
    ilit
    0.65
    ivia
    0.63
    english
    0.60
    unte
    0.60
    sylv
    0.58
    SourceFile
    0.57
    lucent
    0.56
    rote
    0.56
    rete
    0.53
    ¶æ
    0.52
    Activations Density 3.085%

    No Known Activations