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. 1244
    Prev
    Next
    INDEX
    Explanations

    bill numbers

    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
    447
    +0.12
    0.6%
    314
    +0.11
    0.5%
    197
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    719
    +0.12
    0.03
    388
    +0.11
    0.02
    197
    +0.11
    0.02
    Negative Logits
    tones
    -0.70
     Nanto
    -0.64
    >[
    -0.61
     depths
    -0.60
     distance
    -0.60
     disturbances
    -0.60
     abyss
    -0.60
     swast
    -0.59
     loyal
    -0.59
     foss
    -0.59
    POSITIVE LOGITS
    HB
    0.80
    783
    0.80
    è¦ļéĨĴ
    0.79
    ĨĴ
    0.78
    20439
    0.77
    393
    0.76
    753
    0.73
    793
    0.73
    772
    0.72
    262
    0.72
    Activations Density 0.056%

    No Known Activations