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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 1536
    9. 8-RES_FS1536-JB
    11. 1121
    Prev
    Next
    INDEX
    Explanations

    events and locations in a documentary context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    194
    +0.12
    0.6%
    425
    +0.10
    0.5%
    181
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.12
    0.06
    296
    +0.10
    0.07
    608
    +0.10
    0.08
    Negative Logits
    mine
    -0.67
    blance
    -0.66
    resy
    -0.63
    ACTION
    -0.62
    rored
    -0.60
    Statement
    -0.58
    Foot
    -0.58
    \.
    -0.57
    Money
    -0.57
    ICAL
    -0.55
    POSITIVE LOGITS
     onward
    0.95
     onwards
    0.90
     inception
    0.84
     beginnings
    0.77
     to
    0.74
     beginner
    0.61
     benign
    0.61
     To
    0.60
    OPA
    0.60
     obscurity
    0.59
    Activations Density 1.476%

    No Known Activations