© 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 12288
    9. 8-RES_FS12288-JB
    11. 358
    Prev
    Next
    INDEX
    Explanations

    adjectives describing attributes or behaviors of individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    195
    +0.17
    0.8%
    183
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.17
    0.04
    178
    +0.11
    0.05
    603
    +0.10
    0.04
    Negative Logits
    estern
    -0.88
    ests
    -0.74
    ilts
    -0.71
    ainers
    -0.66
    ioch
    -0.65
     Fahrenheit
    -0.63
    ribution
    -0.63
    atform
    -0.61
    EStreamFrame
    -0.61
     ABE
    -0.61
    POSITIVE LOGITS
     oddly
    0.92
     awfully
    0.90
     poised
    0.89
     innocuous
    0.88
     strangely
    0.88
     unstoppable
    0.82
     like
    0.81
    rils
    0.79
    Pause
    0.79
     confused
    0.78
    Activations Density 0.092%

    No Known Activations