© 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. 13510
    Prev
    Next
    INDEX
    Explanations

    information related to public infrastructure issues and government problems

    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
    581
    +0.12
    0.5%
    214
    +0.10
    0.5%
    163
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.12
    0.04
    163
    +0.10
    0.03
    288
    +0.10
    0.04
    Negative Logits
    iths
    -0.74
    stals
    -0.69
    ounded
    -0.68
    zos
    -0.64
    aughs
    -0.64
    lations
    -0.64
    poons
    -0.63
     Clouds
    -0.61
    hua
    -0.60
    ItemTracker
    -0.60
    POSITIVE LOGITS
     imaginable
    1.71
     conceivable
    1.18
     except
    1.09
     whatsoever
    0.97
    soever
    0.87
    except
    0.81
     irrespective
    0.78
     ounce
    0.76
     regardless
    0.74
    winner
    0.73
    Activations Density 0.161%

    No Known Activations