© 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. 20010
    Prev
    Next
    INDEX
    Explanations

    email-related terms and actions

    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
    311
    +0.12
    0.5%
    755
    +0.11
    0.5%
    490
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.12
    0.03
    490
    +0.11
    0.03
    665
    +0.10
    0.03
    Negative Logits
     Tradition
    -0.71
     Parents
    -0.66
     Kendall
    -0.62
     secrecy
    -0.57
     lineback
    -0.56
     Technique
    -0.56
     Emanuel
    -0.56
     Mother
    -0.55
    lication
    -0.55
    bard
    -0.54
    POSITIVE LOGITS
    bodied
    1.04
    ioned
    0.93
    't
    0.90
    iary
    0.74
     access
    0.74
    reys
    0.73
     afford
    0.72
    ãĥĪ
    0.72
    ãĥģ
    0.72
    ny
    0.72
    Activations Density 0.035%

    No Known Activations