© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37244
    Prev
    Next
    INDEX
    Explanations

    locations and settings in narratives

    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
    489
    +0.10
    0.5%
    642
    +0.10
    0.5%
    447
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.10
    0.03
    362
    +0.10
    0.03
    624
    +0.09
    0.02
    Negative Logits
     Flavoring
    -0.87
    pkg
    -0.82
     actionGroup
    -0.80
     sniff
    -0.73
    cipled
    -0.72
    Marginal
    -0.71
     brakes
    -0.70
     enzyme
    -0.70
    omore
    -0.69
     enzymes
    -0.68
    POSITIVE LOGITS
     dystopian
    1.32
     dystop
    1.19
     fictional
    1.10
     backdrop
    1.10
     futuristic
    0.95
     ruins
    0.92
     medieval
    0.92
     countryside
    0.91
     feudal
    0.89
     Gothic
    0.88
    Activations Density 0.168%

    No Known Activations