© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    text related to programming code, specifically regarding accessing tokens and accessing services

    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
    642
    +0.10
    0.5%
    212
    +0.10
    0.4%
    329
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.04
    212
    +0.10
    0.04
    578
    +0.10
    0.02
    Negative Logits
    ository
    -0.76
    iazep
    -0.73
     logistics
    -0.71
    EH
    -0.70
    GV
    -0.70
     dispatched
    -0.69
     CPR
    -0.67
    urdue
    -0.67
    quest
    -0.66
    =-=-=-=-
    -0.66
    POSITIVE LOGITS
     colors
    1.44
     colours
    1.36
     color
    1.36
     colour
    1.32
     brighter
    1.31
     tint
    1.26
     bright
    1.22
     Colors
    1.20
     hue
    1.19
     orange
    1.17
    Activations Density 0.446%

    No Known Activations