© 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 49152
    9. 8-RES_FS49152-JB
    11. 45679
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Biden"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    59
    +0.12
    0.6%
    183
    +0.11
    0.5%
    302
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    302
    +0.11
    0.01
    683
    +0.10
    0.01
    Negative Logits
     exha
    -0.82
     murd
    -0.80
     rul
    -0.75
     Rita
    -0.73
    pmwiki
    -0.72
    psc
    -0.69
     retard
    -0.69
     includ
    -0.68
     destro
    -0.67
     ILCS
    -0.67
    POSITIVE LOGITS
    vironment
    1.11
    ovo
    0.94
    iden
    0.93
    zyme
    0.91
    omics
    0.91
    fold
    0.91
    vier
    0.86
    feld
    0.85
    mire
    0.85
    ously
    0.85
    Activations Density 0.007%

    No Known Activations