© 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. 37370
    Prev
    Next
    INDEX
    Explanations

    references to social hierarchy and class distinctions

    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
    447
    +0.18
    0.8%
    721
    +0.10
    0.4%
    556
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.18
    0.02
    752
    +0.10
    0.03
    747
    +0.10
    0.02
    Negative Logits
    bats
    -0.86
    DAY
    -0.78
    urbed
    -0.73
    risome
    -0.71
    GUI
    -0.71
    kees
    -0.70
    Merit
    -0.69
    thirst
    -0.67
    indust
    -0.67
    natureconservancy
    -0.65
    POSITIVE LOGITS
    endment
    0.81
    imester
    0.74
    KO
    0.70
     onwards
    0.68
     Misty
    0.67
    enium
    0.65
     KO
    0.64
     foremost
    0.63
     approximation
    0.63
    eve
    0.62
    Activations Density 0.082%

    No Known Activations