© 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. 7108
    Prev
    Next
    INDEX
    Explanations

    references to rounds or stages of a competition or event

    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
    157
    +0.14
    0.7%
    162
    +0.12
    0.5%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.14
    0.03
    162
    +0.12
    0.02
    500
    +0.11
    0.02
    Negative Logits
     streng
    -0.67
    kson
    -0.66
    ufact
    -0.65
    yer
    -0.64
    uras
    -0.63
    ãĤ¿
    -0.62
    vell
    -0.61
     Jong
    -0.60
    aith
    -0.60
     Hots
    -0.60
    POSITIVE LOGITS
    trip
    1.03
    table
    0.97
     rob
    0.95
    abouts
    0.92
    about
    0.89
    stakes
    0.89
    worms
    0.82
    meal
    0.82
    outs
    0.81
    naire
    0.81
    Activations Density 0.017%

    No Known Activations