© 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. 37178
    Prev
    Next
    INDEX
    Explanations

    references to specific regions or movements associated with social or political issues

    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
    7
    +0.14
    0.6%
    503
    +0.12
    0.6%
    767
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.14
    0.01
    503
    +0.12
    0.01
    7
    +0.10
    0.01
    Negative Logits
    DEN
    -0.66
    chy
    -0.64
    giving
    -0.63
     STATS
    -0.61
    LOAD
    -0.60
     stale
    -0.60
    à©
    -0.60
    mberg
    -0.60
    choes
    -0.59
    STER
    -0.59
    POSITIVE LOGITS
    adia
    1.16
    ribed
    1.07
    adian
    1.02
    ott
    0.97
    inating
    0.91
    henko
    0.90
    otte
    0.90
    pite
    0.89
    inated
    0.89
    ents
    0.88
    Activations Density 0.004%

    No Known Activations