© 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. 4405
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and software release information

    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
    615
    +0.10
    0.5%
    68
    +0.10
    0.5%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    615
    +0.10
    0.03
    680
    +0.10
    0.02
    601
    +0.10
    0.02
    Negative Logits
     purse
    -0.70
     striking
    -0.70
     framing
    -0.69
     gull
    -0.65
     deduct
    -0.63
     shutter
    -0.63
     worsh
    -0.63
     cradle
    -0.61
     anecdote
    -0.60
     carpet
    -0.60
    POSITIVE LOGITS
    0
    1.28
    5
    1.09
    02
    1.03
    04
    1.03
    x
    1.00
    03
    1.00
    3
    0.99
    4
    0.97
    00
    0.96
    6
    0.95
    Activations Density 0.056%

    No Known Activations