© 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. 14632
    Prev
    Next
    INDEX
    Explanations

    medical terminology and words related to technology and software development

    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
    569
    +0.14
    0.7%
    649
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    569
    +0.14
    0.02
    343
    +0.11
    0.02
    659
    +0.10
    0.02
    Negative Logits
    phrine
    -0.67
     Adin
    -0.65
     behavi
    -0.64
     celebr
    -0.64
     Malf
    -0.63
     Bene
    -0.60
     unlaw
    -0.59
     Polly
    -0.58
     disobedience
    -0.58
     Qur
    -0.58
    POSITIVE LOGITS
    orea
    1.23
    ernel
    1.20
    istani
    1.03
    EEP
    1.02
    eeper
    1.01
    won
    0.98
    laus
    0.97
    enzie
    0.91
    regate
    0.91
    orean
    0.90
    Activations Density 0.033%

    No Known Activations