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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26176
    Prev
    Next
    INDEX
    Explanations

    instances of preparation and initiation of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    147
    +0.10
    0.5%
    337
    +0.10
    0.5%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    337
    +0.10
    0.03
    113
    +0.10
    0.03
    157
    +0.09
    0.03
    Negative Logits
    >.
    -0.72
    MON
    -0.68
     altogether
    -0.65
    unless
    -0.65
    tec
    -0.63
    $.
    -0.62
    illegal
    -0.62
    found
    -0.62
    collar
    -0.60
    CN
    -0.59
    POSITIVE LOGITS
     dwindling
    0.82
     unfolds
    0.72
     unfold
    0.72
     intens
    0.72
     progresses
    0.70
     dusk
    0.70
     fading
    0.69
     dawn
    0.68
     fades
    0.68
     twilight
    0.68
    Activations Density 0.113%

    No Known Activations