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 24576
    5. 8-RES_FS24576-JB
    6. 968
    Prev
    Next
    INDEX
    Explanations

    dates and specific timeframes in the text

    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
    380
    +0.10
    0.5%
    339
    +0.10
    0.4%
    156
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.10
    0.03
    380
    +0.10
    0.03
    301
    +0.09
    0.03
    Negative Logits
    odor
    -0.69
    ocracy
    -0.67
    haar
    -0.63
    lua
    -0.63
    Bal
    -0.60
    rw
    -0.59
     Jehovah
    -0.59
     Religion
    -0.59
     Entered
    -0.59
    DNA
    -0.59
    POSITIVE LOGITS
     versions
    0.95
    etheless
    0.92
     stages
    0.90
     generations
    0.88
     iterations
    0.88
    noon
    0.87
     installments
    0.87
     editions
    0.86
    iations
    0.85
    than
    0.84
    Activations Density 0.029%

    No Known Activations