© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4025
    Prev
    Next
    INDEX
    Explanations

    mentions of fine details or distinctions in various topics or industries

    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
    63
    +0.13
    0.6%
    620
    +0.12
    0.5%
    284
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    63
    +0.13
    0.02
    620
    +0.12
    0.01
    284
    +0.11
    0.02
    Negative Logits
    jri
    -0.81
    ulhu
    -0.79
    rush
    -0.78
    urg
    -0.75
    MJ
    -0.74
     Kut
    -0.74
    leaders
    -0.73
    ocide
    -0.73
    omorphic
    -0.72
    soDeliveryDate
    -0.71
    POSITIVE LOGITS
     Gael
    1.10
     tuning
    1.08
     tuned
    0.96
     tune
    0.83
     linen
    0.82
     arts
    0.79
     dining
    0.79
     fine
    0.77
    Fine
    0.76
    baum
    0.75
    Activations Density 0.017%

    No Known Activations