© 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. 25805
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" indicating spatial or contextual relationships

    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
    640
    +0.12
    0.5%
    123
    +0.11
    0.5%
    585
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.12
    0.05
    469
    +0.11
    0.04
    29
    +0.09
    0.04
    Negative Logits
    killed
    -0.85
    username
    -0.74
    plate
    -0.63
    kill
    -0.60
     ALSO
    -0.60
    LER
    -0.59
     Presbyter
    -0.59
    enn
    -0.59
     Seller
    -0.58
    heet
    -0.58
    POSITIVE LOGITS
     circles
    1.15
     unison
    1.08
    animate
    0.99
     vain
    0.97
     pursuit
    0.96
     accordance
    0.95
     anticipation
    0.95
     front
    0.93
     tandem
    0.92
     relation
    0.88
    Activations Density 0.097%

    No Known Activations