© 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. 12047
    Prev
    Next
    INDEX
    Explanations

    acronyms and numerical values that are repeated in a sequence

    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
    314
    +0.10
    0.5%
    116
    +0.10
    0.4%
    649
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.10
    0.03
    667
    +0.10
    0.03
    326
    +0.10
    0.02
    Negative Logits
     blur
    -0.85
     ric
    -0.83
     gent
    -0.79
     plent
    -0.79
     sid
    -0.77
     ancest
    -0.74
     adam
    -0.73
     sher
    -0.71
     sausage
    -0.71
     princ
    -0.71
    POSITIVE LOGITS
    KA
    1.21
    PT
    1.17
    ING
    1.17
    AX
    1.17
    RD
    1.15
    TED
    1.14
    ROR
    1.13
    DERR
    1.13
    PAC
    1.11
    OUT
    1.11
    Activations Density 0.065%

    No Known Activations