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. 26197
    Prev
    Next
    INDEX
    Explanations

    the word "generally" and its variations, indicating a focus on general statements or observations

    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
    114
    +0.11
    0.5%
    208
    +0.11
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.11
    0.02
    114
    +0.11
    0.02
    151
    +0.10
    0.02
    Negative Logits
    ÄŁ
    -0.75
    ilion
    -0.75
     Frenzy
    -0.70
    acity
    -0.70
     Tycoon
    -0.69
    lyn
    -0.69
    yles
    -0.68
    yle
    -0.66
    illion
    -0.66
    lez
    -0.66
    POSITIVE LOGITS
     speaking
    1.22
     regarded
    1.00
     frowned
    0.90
     accepted
    0.88
     disliked
    0.83
     disappro
    0.77
     appreciated
    0.76
    WAYS
    0.76
     viewed
    0.76
    speaking
    0.76
    Activations Density 0.015%

    No Known Activations