© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 15647
    Prev
    Next
    INDEX
    Explanations

    mentions of and instructions related to demos

    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
    167
    +0.14
    0.6%
    288
    +0.13
    0.6%
    270
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.14
    0.01
    288
    +0.13
    0.01
    500
    +0.12
    0.01
    Negative Logits
    turn
    -0.74
    leans
    -0.65
    capacity
    -0.64
    olia
    -0.64
    adia
    -0.64
    ricanes
    -0.63
    Else
    -0.62
    aucas
    -0.61
     Mysteries
    -0.61
    sea
    -0.61
    POSITIVE LOGITS
     reel
    0.98
    eer
    0.90
    stration
    0.87
     demo
    0.81
    psey
    0.79
     tapes
    0.79
    ery
    0.78
     suite
    0.78
     sessions
    0.77
    spective
    0.76
    Activations Density 0.019%

    No Known Activations