© 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. 8562
    Prev
    Next
    INDEX
    Explanations

    conjunctions like 'and' or 'or'

    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
    290
    +0.13
    0.6%
    340
    +0.10
    0.4%
    300
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.13
    0.02
    340
    +0.10
    0.02
    746
    +0.09
    0.02
    Negative Logits
     Petr
    -0.68
    illi
    -0.66
     Registry
    -0.65
     Standards
    -0.58
     Journals
    -0.58
     Kard
    -0.58
    gur
    -0.57
    WARE
    -0.56
     Romeo
    -0.56
    ware
    -0.56
    POSITIVE LOGITS
    ecycle
    0.76
    asus
    0.75
    rogen
    0.74
    Interstitial
    0.72
    present
    0.71
    romeda
    0.71
     aft
    0.70
    rogens
    0.69
    isode
    0.68
    behind
    0.67
    Activations Density 0.049%

    No Known Activations