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. 23818
    Prev
    Next
    INDEX
    Explanations

    references to rain and rainy weather conditions

    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
    7
    +0.12
    0.6%
    739
    +0.12
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.12
    0.02
    7
    +0.12
    0.02
    15
    +0.10
    0.02
    Negative Logits
    ovo
    -0.83
    entric
    -0.79
    ernel
    -0.76
    VICE
    -0.73
    ancial
    -0.73
    orea
    -0.72
    atown
    -0.70
    ó
    -0.67
    umbn
    -0.66
     Keen
    -0.66
    POSITIVE LOGITS
    bows
    1.65
    forest
    1.38
    drops
    1.37
    storms
    1.15
    water
    1.15
    storm
    1.10
    bow
    1.08
    drop
    1.05
     showers
    1.01
    falls
    0.99
    Activations Density 0.021%

    No Known Activations