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 1536
    5. 8-RES_FS1536-JB
    6. 588
    Prev
    Next
    INDEX
    Explanations

    stories or narratives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    160
    +0.13
    0.6%
    756
    +0.10
    0.5%
    6
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.09
    651
    +0.10
    0.08
    160
    +0.10
    0.09
    Negative Logits
    orem
    -0.84
    ignt
    -0.80
    inence
    -0.78
    bledon
    -0.77
    hammad
    -0.75
    achev
    -0.72
    aurus
    -0.70
    owered
    -0.70
    amily
    -0.68
    ynski
    -0.68
    POSITIVE LOGITS
    telling
    1.29
     arcs
    1.02
    te
    0.99
     arc
    0.97
    tell
    0.86
    book
    0.85
    tale
    0.84
     involving
    0.83
     reprinted
    0.83
     synopsis
    0.82
    Activations Density 1.937%

    No Known Activations