© 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. 726
    Prev
    Next
    INDEX
    Explanations

    URLs or website links

    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
    373
    +0.16
    0.8%
    174
    +0.12
    0.6%
    208
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.16
    0.03
    381
    +0.12
    0.03
    208
    +0.11
    0.03
    Negative Logits
    senal
    -0.60
     numbering
    -0.60
     Fortune
    -0.60
    luster
    -0.59
    conservancy
    -0.57
    quartered
    -0.56
     substitutes
    -0.55
     recovering
    -0.54
     cosmetic
    -0.54
     successor
    -0.54
    POSITIVE LOGITS
    /_
    0.92
    /#
    0.84
    nw
    0.70
    /?
    0.70
    cdn
    0.69
    mAh
    0.67
    EH
    0.65
    yg
    0.64
    000000
    0.64
    /-
    0.63
    Activations Density 0.028%

    No Known Activations