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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 5466
    Prev
    Next
    INDEX
    Explanations

    studies and research findings related to various topics and social issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    447
    +0.12
    0.5%
    575
    +0.11
    0.5%
    651
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    574
    +0.12
    0.03
    651
    +0.11
    0.04
    419
    +0.10
    0.04
    Negative Logits
    rising
    -0.70
    fw
    -0.62
    ansas
    -0.60
    gc
    -0.59
     fitt
    -0.58
     chopping
    -0.56
     wedding
    -0.56
     Reyn
    -0.55
     Leilan
    -0.55
     Garland
    -0.54
    POSITIVE LOGITS
     conducted
    0.95
    udo
    0.93
    study
    0.86
    Study
    0.82
     Subjects
    0.81
     abroad
    0.77
     published
    0.76
    iatrics
    0.75
     undertaken
    0.74
     methodology
    0.72
    Activations Density 0.168%

    No Known Activations