© 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 24576
    9. 8-RES_FS24576-JB
    11. 22146
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate new developments, products, or features

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.17
    0.8%
    608
    +0.11
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.17
    0.05
    362
    +0.11
    0.05
    172
    +0.11
    0.03
    Negative Logits
    cia
    -0.74
    assian
    -0.72
    ossibility
    -0.70
    /-
    -0.69
    ivia
    -0.69
    heit
    -0.68
    emies
    -0.68
    olson
    -0.67
     bothered
    -0.66
    strate
    -0.65
    POSITIVE LOGITS
     regards
    0.98
     regard
    0.78
     nominations
    0.77
     unveiling
    0.76
     announcements
    0.74
     additions
    0.74
     acquisitions
    0.72
     offerings
    0.72
     visuals
    0.71
     selections
    0.71
    Activations Density 0.218%

    No Known Activations