© 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. 2421
    Prev
    Next
    INDEX
    Explanations

    astronomical and medical terminology

    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
    659
    +0.11
    0.5%
    222
    +0.09
    0.4%
    759
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    575
    +0.09
    0.06
    325
    +0.09
    0.05
    Negative Logits
     Hond
    -0.72
     Berm
    -0.60
     Ack
    -0.59
     Maurit
    -0.58
     Cary
    -0.58
     Cran
    -0.58
    estern
    -0.57
     pestic
    -0.56
     Pyr
    -0.56
     Nex
    -0.56
    POSITIVE LOGITS
    </
    0.90
    *,
    0.80
    âĢ
    0.80
    [/
    0.80
    *.
    0.74
    .</
    0.74
    .–
    0.72
     ().
    0.71
     counterpart
    0.69
    0.69
    Activations Density 0.416%

    No Known Activations