© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37208
    Prev
    Next
    INDEX
    Explanations

    occurrences of numbers, particularly emphasizing the digits "six" and "seven"

    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
    289
    +0.11
    0.5%
    71
    +0.10
    0.5%
    1
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.11
    0.05
    183
    +0.10
    0.04
    609
    +0.10
    0.04
    Negative Logits
    ACTION
    -0.71
    Hub
    -0.67
    OCK
    -0.66
    vantage
    -0.66
    lance
    -0.66
    auc
    -0.65
    geist
    -0.64
    LAN
    -0.62
    /_
    -0.62
    rm
    -0.62
    POSITIVE LOGITS
    teenth
    1.76
    teen
    1.73
    een
    1.37
    fold
    1.36
    eenth
    1.36
     hundred
    1.31
     thousand
    1.22
     months
    1.13
    ieth
    1.06
    acious
    1.02
    Activations Density 0.073%

    No Known Activations