© 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 12288
    9. 8-RES_FS12288-JB
    11. 9499
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives with negative connotations

    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
    616
    +0.12
    0.5%
    195
    +0.10
    0.5%
    156
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.12
    0.05
    326
    +0.10
    0.04
    331
    +0.09
    0.05
    Negative Logits
     prisoner
    -0.66
     walk
    -0.62
     wedding
    -0.60
     reckoning
    -0.60
     reconciliation
    -0.59
     sleeper
    -0.59
     Settlement
    -0.59
     settlement
    -0.59
     backs
    -0.58
     payday
    -0.58
    POSITIVE LOGITS
    uously
    1.49
    ately
    1.41
    iously
    1.38
    ously
    1.36
    ingly
    1.35
    ibly
    1.35
    uably
    1.31
    ably
    1.27
    antly
    1.27
    ivably
    1.27
    Activations Density 0.242%

    No Known Activations