© 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. 9441
    Prev
    Next
    INDEX
    Explanations

    terms related to medical substances or procedures and numerical patterns

    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
    67
    +0.11
    0.5%
    81
    +0.11
    0.5%
    578
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.11
    0.01
    232
    +0.11
    0.01
    343
    +0.10
    0.01
    Negative Logits
     Democr
    -0.79
     Pixie
    -0.76
    UCT
    -0.75
    xual
    -0.72
    EngineDebug
    -0.71
     Canary
    -0.68
    ORED
    -0.65
    hetti
    -0.65
    ++++
    -0.65
     Extrem
    -0.64
    POSITIVE LOGITS
    ration
    1.09
     Lumpur
    0.95
    acter
    0.94
    rils
    0.92
    acles
    0.91
    ril
    0.91
    ormal
    0.90
    stal
    0.89
    wh
    0.88
    raine
    0.86
    Activations Density 0.013%

    No Known Activations