© 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. 8505
    Prev
    Next
    INDEX
    Explanations

    the word "catch" in various contexts

    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
    1
    +0.14
    0.7%
    314
    +0.12
    0.6%
    59
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.14
    0.03
    59
    +0.12
    0.02
    297
    +0.12
    0.02
    Negative Logits
    bard
    -0.63
     princip
    -0.61
    sburgh
    -0.58
     annex
    -0.58
    die
    -0.58
    htar
    -0.58
    inburgh
    -0.57
     coerc
    -0.57
    enstein
    -0.57
    burgh
    -0.57
    POSITIVE LOGITS
    phrase
    1.08
    netflix
    0.77
     glimps
    0.73
    tails
    0.72
    ipes
    0.72
    weight
    0.71
    tail
    0.68
     Luffy
    0.68
    weights
    0.68
    amac
    0.68
    Activations Density 0.022%

    No Known Activations