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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 40067
    Prev
    Next
    INDEX
    Explanations

    variations of the word "take" in different contexts

    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
    240
    +0.11
    0.5%
    155
    +0.11
    0.5%
    611
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.11
    0.02
    611
    +0.11
    0.02
    240
    +0.10
    0.02
    Negative Logits
     advertised
    -0.73
     constitu
    -0.71
     livest
    -0.69
     destro
    -0.67
     accompanies
    -0.67
     warr
    -0.63
     agre
    -0.63
     convol
    -0.62
    iege
    -0.62
    ambo
    -0.61
    POSITIVE LOGITS
    aways
    1.46
    away
    1.14
    overs
    1.02
     heed
    1.00
    uchi
    0.94
    prising
    0.88
     advantage
    0.85
     aback
    0.81
    prise
    0.80
     care
    0.78
    Activations Density 0.019%

    No Known Activations