© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    sentences discussing personal opinions or perspectives within a context

    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
    447
    +0.17
    0.8%
    55
    +0.12
    0.6%
    102
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.17
    0.09
    102
    +0.12
    0.09
    718
    +0.12
    0.07
    Negative Logits
    upt
    -0.71
    seys
    -0.64
     talks
    -0.63
    cul
    -0.61
     floats
    -0.61
     Talks
    -0.61
    aths
    -0.60
    culosis
    -0.59
    regate
    -0.58
    sheet
    -0.58
    POSITIVE LOGITS
     borne
    0.92
     sorely
    0.85
     echoed
    0.84
     happening
    0.84
     reflected
    0.83
     pervasive
    0.81
     manifested
    0.81
     replicated
    0.80
     contrasted
    0.79
     accompanied
    0.78
    Activations Density 0.455%

    No Known Activations