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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4856
    Prev
    Next
    INDEX
    Explanations

    email-related actions

    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
    59
    +0.12
    0.5%
    649
    +0.10
    0.5%
    366
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.12
    0.04
    439
    +0.10
    0.03
    654
    +0.10
    0.03
    Negative Logits
    heid
    -0.97
    profit
    -0.79
    urity
    -0.74
    tera
    -0.70
    itect
    -0.69
    iferation
    -0.66
    olar
    -0.64
     concentrating
    -0.64
    urities
    -0.64
    ibur
    -0.63
    POSITIVE LOGITS
     condolences
    1.03
     messages
    1.01
     Emails
    0.99
     emails
    0.99
     notifications
    0.98
     correspondence
    0.96
    mail
    0.96
     invitations
    0.95
     mail
    0.94
     email
    0.94
    Activations Density 0.066%

    No Known Activations