Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11399
    Prev
    Next
    INDEX
    Explanations

    medical terms related to vision and ocular health

    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
    308
    +0.12
    0.5%
    549
    +0.12
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.12
    0.01
    503
    +0.12
    0.01
    549
    +0.10
    0.01
    Negative Logits
    creen
    -0.92
    wagen
    -0.78
    LESS
    -0.77
    baum
    -0.73
    IELD
    -0.72
    hift
    -0.70
    cake
    -0.69
     Zucker
    -0.68
    å§«
    -0.66
    Shock
    -0.66
    POSITIVE LOGITS
    uders
    1.19
    uding
    1.12
    usions
    1.04
    aband
    1.04
    inx
    1.02
    usted
    0.99
    igent
    0.96
    agg
    0.95
    acent
    0.95
    iencies
    0.94
    Activations Density 0.016%

    No Known Activations