© 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. 37256
    Prev
    Next
    INDEX
    Explanations

    references to geographic regions and communities

    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
    481
    +0.28
    1.5%
    87
    +0.21
    1.1%
    219
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.28
    0.04
    616
    +0.21
    0.04
    596
    +0.12
    0.04
    Negative Logits
     Reincarn
    -0.69
     infall
    -0.69
    potion
    -0.63
     translator
    -0.63
    Prof
    -0.63
     torture
    -0.62
     Gest
    -0.61
     Freud
    -0.61
     exorc
    -0.60
    fn
    -0.60
    POSITIVE LOGITS
     suburbs
    1.16
     counties
    1.15
     districts
    1.13
     southwestern
    1.11
     southwest
    1.10
     rural
    1.10
     neighborhoods
    1.08
     northeastern
    1.08
     northwest
    1.07
     northeast
    1.04
    Activations Density 0.331%

    No Known Activations