© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19521
    Prev
    Next
    INDEX
    Explanations

    contractions indicating negation or abbreviation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    102
    +0.12
    0.5%
    512
    +0.10
    0.4%
    643
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.12
    0.04
    200
    +0.10
    0.04
    437
    +0.09
    0.03
    Negative Logits
    çļ
    -0.88
    çīĪ
    -0.74
    èĪ
    -0.73
    è¦ļéĨĴ
    -0.73
    inav
    -0.73
    æĥ
    -0.69
    obo
    -0.69
    çĶŁ
    -0.68
    velt
    -0.68
    onyms
    -0.68
    POSITIVE LOGITS
     necessarily
    1.37
     exactly
    1.22
     gonna
    1.13
     bothering
    1.05
     quite
    1.04
    icable
    1.00
     supposed
    0.98
     really
    0.96
     bothered
    0.94
     terribly
    0.93
    Activations Density 0.063%

    No Known Activations