© 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 24576
    9. 8-RES_FS24576-JB
    11. 18854
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or events happening sequentially

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    679
    +0.14
    0.6%
    290
    +0.12
    0.5%
    665
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.14
    0.03
    361
    +0.12
    0.03
    665
    +0.11
    0.03
    Negative Logits
    voy
    -0.76
    vil
    -0.74
    utor
    -0.71
    ldom
    -0.71
    flo
    -0.69
    adin
    -0.69
    tu
    -0.69
    uci
    -0.68
    ukong
    -0.67
    ancing
    -0.66
    POSITIVE LOGITS
     suit
    1.08
     closely
    0.94
    suit
    0.88
    ĸļ
    0.84
     footsteps
    0.73
     logically
    0.70
     faithfully
    0.66
     Suit
    0.65
    SHIP
    0.65
    :]
    0.64
    Activations Density 0.032%

    No Known Activations