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. 1323
    Prev
    Next
    INDEX
    Explanations

    references to newness or recent development

    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
    339
    +0.11
    0.5%
    362
    +0.10
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.11
    0.09
    489
    +0.10
    0.08
    499
    +0.09
    0.07
    Negative Logits
    xual
    -0.76
    acebook
    -0.74
    Zip
    -0.70
    cius
    -0.69
    ouse
    -0.68
    osure
    -0.66
    ashtra
    -0.66
    agree
    -0.65
    lua
    -0.64
    veyard
    -0.64
    POSITIVE LOGITS
    bie
    1.46
    bies
    1.46
     arrivals
    1.25
    foundland
    1.11
     additions
    1.01
     batch
    0.95
     entrants
    0.95
     generation
    0.93
     Zealand
    0.93
     millennium
    0.92
    Activations Density 0.831%

    No Known Activations