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. 23226
    Prev
    Next
    INDEX
    Explanations

    instances of anonymous references

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.12
    0.6%
    385
    +0.12
    0.6%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.12
    0.01
    399
    +0.12
    0.01
    585
    +0.10
    0.01
    Negative Logits
    ombo
    -0.81
     Gork
    -0.81
    meaning
    -0.80
    eele
    -0.78
    asters
    -0.76
    lda
    -0.75
    eled
    -0.74
    grain
    -0.73
    matically
    -0.73
    =-=-=-=-=-=-=-=-
    -0.71
    POSITIVE LOGITS
     Warfare
    0.69
    Party
    0.69
    username
    0.69
     obliged
    0.68
    ãĥĩ
    0.67
     Anonymous
    0.66
    onym
    0.62
    ica
    0.62
    Person
    0.62
    ITY
    0.62
    Activations Density 0.019%

    No Known Activations