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. 18987
    Prev
    Next
    INDEX
    Explanations

    instances of the word "signature."

    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
    679
    +0.13
    0.6%
    538
    +0.11
    0.5%
    193
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.13
    0.01
    592
    +0.11
    0.01
    381
    +0.10
    0.01
    Negative Logits
    aiman
    -0.81
    anus
    -0.80
    »Ĵ
    -0.74
    isen
    -0.73
    awar
    -0.73
    edia
    -0.73
    frey
    -0.72
    itals
    -0.69
    ĸļ
    -0.68
    artment
    -0.68
    POSITIVE LOGITS
    atures
    0.91
    ATURE
    0.88
    ificant
    0.84
    boards
    0.79
    board
    0.78
    ATURES
    0.78
    ature
    0.77
    */(
    0.76
     signature
    0.71
     signatures
    0.71
    Activations Density 0.020%

    No Known Activations