© 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. 19428
    Prev
    Next
    INDEX
    Explanations

    the word "Liberator" or its variations

    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
    288
    +0.16
    0.7%
    238
    +0.10
    0.5%
    692
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.01
    627
    +0.10
    0.01
    677
    +0.10
    0.01
    Negative Logits
    soDeliveryDate
    -0.80
    enegger
    -0.76
    è¦ļéĨĴ
    -0.70
    older
    -0.70
    ulhu
    -0.65
     Shards
    -0.64
    WAYS
    -0.64
    wow
    -0.62
     Carbuncle
    -0.62
    BOOK
    -0.60
    POSITIVE LOGITS
    tarians
    1.33
    ator
    1.06
    tarian
    1.06
    gence
    1.02
    ations
    0.98
    ated
    0.98
    ators
    0.95
    itas
    0.94
    aine
    0.91
    mented
    0.90
    Activations Density 0.020%

    No Known Activations