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. 21782
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and ingredient quantities

    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
    481
    +0.43
    2.1%
    447
    +0.14
    0.7%
    551
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.43
    0.05
    726
    +0.14
    0.05
    39
    +0.10
    0.05
    Negative Logits
    Sund
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.58
    roots
    -0.55
    apons
    -0.54
     comr
    -0.54
    rig
    -0.53
     commod
    -0.53
     cumbers
    -0.52
    ãĥ©ãĥ³
    -0.52
    duino
    -0.51
    POSITIVE LOGITS
    <|endoftext|>
    0.80
    .
    0.74
    .).
    0.72
    .):
    0.70
     :)
    0.68
    ↵↵
    0.68
    .)
    0.68
    .>>
    0.67
     XD
    0.67
    .),
    0.66
    Activations Density 0.405%

    No Known Activations