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. 705
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Chris

    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
    459
    +0.14
    0.7%
    208
    +0.11
    0.5%
    343
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.18
    326
    +0.11
    0.15
    343
    +0.10
    0.09
    Negative Logits
    etheless
    -0.73
     externalToEVAOnly
    -0.73
     recip
    -0.70
    theless
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.67
    orrow
    -0.66
    ipop
    -0.66
    ascus
    -0.65
    duction
    -0.62
    ipolar
    -0.62
    POSITIVE LOGITS
    lihood
    0.90
    rament
    0.90
    bridge
    0.89
    ivities
    0.80
    rophe
    0.77
    room
    0.76
    water
    0.74
    ieve
    0.73
    ABLE
    0.73
    hold
    0.72
    Activations Density 3.380%

    No Known Activations