© 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. 7114
    Prev
    Next
    INDEX
    Explanations

    Facebook profiles

    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
    585
    +0.10
    0.4%
    541
    +0.10
    0.4%
    672
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.10
    0.03
    508
    +0.10
    0.03
    609
    +0.10
    0.03
    Negative Logits
    Downloadha
    -0.74
     Guardiola
    -0.68
    aples
    -0.66
    riel
    -0.64
    OPA
    -0.62
    riott
    -0.61
     circumcised
    -0.61
     Thatcher
    -0.61
    iola
    -0.60
    dinand
    -0.60
    POSITIVE LOGITS
     username
    1.06
     page
    0.96
     account
    0.93
     postings
    0.90
     timeline
    0.90
     hashtag
    0.89
     profile
    0.88
     persona
    0.83
     webpage
    0.82
     message
    0.81
    Activations Density 0.097%

    No Known Activations