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. 41292
    Prev
    Next
    INDEX
    Explanations

    references to large groups of people

    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
    71
    +0.11
    0.5%
    718
    +0.10
    0.5%
    294
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.11
    0.03
    689
    +0.10
    0.03
    544
    +0.09
    0.03
    Negative Logits
    Interstitial
    -0.76
    inventoryQuantity
    -0.75
    ãĥ¤
    -0.73
    agate
    -0.72
     Redemption
    -0.70
    iban
    -0.69
    shit
    -0.65
    Delivery
    -0.63
     hegemony
    -0.63
     Gemini
    -0.62
    POSITIVE LOGITS
    ourcing
    0.96
    ourced
    0.93
     upon
    0.85
     fleeing
    0.85
     of
    0.85
     cheering
    0.82
     marched
    0.81
     marching
    0.81
     mobilized
    0.77
     protesting
    0.75
    Activations Density 0.033%

    No Known Activations