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 49152
    5. 8-RES_FS49152-JB
    6. 43404
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or distance away from a specific event or moment

    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
    696
    +0.11
    0.5%
    589
    +0.10
    0.5%
    615
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    696
    +0.11
    0.01
    589
    +0.10
    0.01
    222
    +0.10
    0.01
    Negative Logits
    nce
    -0.75
    iom
    -0.73
    xual
    -0.72
    inse
    -0.68
     dich
    -0.65
    imar
    -0.64
    cephal
    -0.63
    lua
    -0.63
    ãĤ±
    -0.61
    isms
    -0.61
    POSITIVE LOGITS
     ahead
    0.77
     arrival
    0.73
     landfall
    0.73
    eday
    0.70
    angs
    0.69
     approaching
    0.66
     deadlines
    0.66
     completing
    0.66
    peak
    0.66
     surpass
    0.66
    Activations Density 0.019%

    No Known Activations