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 3072
    5. 8-RES_FS3072-JB
    6. 271
    Prev
    Next
    INDEX
    Explanations

    information related to programming languages and coding practices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    739
    +0.12
    0.5%
    640
    +0.12
    0.5%
    417
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.12
    0.04
    308
    +0.12
    0.04
    640
    +0.11
    0.05
    Negative Logits
    ously
    -0.70
    pace
    -0.63
     laundry
    -0.59
    heet
    -0.59
     fortunes
    -0.59
     makeup
    -0.57
     freshman
    -0.56
    pell
    -0.56
     deduction
    -0.55
    arettes
    -0.55
    POSITIVE LOGITS
    _-
    1.77
    webkit
    1.16
    =-=-=-=-=-=-=-=-
    1.13
    =-=-=-=-
    0.97
     [|
    0.89
    /-
    0.84
    sama
    0.84
    \-
    0.81
    =-=-
    0.79
    Phoenix
    0.79
    Activations Density 0.321%

    No Known Activations