© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    political and sports-related terms

    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
    497
    +0.11
    0.6%
    669
    +0.08
    0.4%
    264
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.11
    0.00
    281
    +0.08
    0.04
    295
    +0.08
    0.04
    Negative Logits
    )?
    -0.62
    Ħ¢
    -0.60
    ":{"
    -0.58
     Canaver
    -0.58
    Merit
    -0.56
    ãĢij
    -0.53
    VERTISEMENT
    -0.53
    )!
    -0.50
    æ©Ł
    -0.50
    DCS
    -0.50
    POSITIVE LOGITS
     whereas
    0.62
    ecause
    0.52
     though
    0.50
    anwhile
    0.50
     but
    0.49
    -,
    0.48
     however
    0.47
     equivalents
    0.47
     removable
    0.46
    +(
    0.45
    Activations Density 1.921%

    No Known Activations