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 49152
    5. 8-RES_FS49152-JB
    6. 26254
    Prev
    Next
    INDEX
    Explanations

    assembly language instructions and code-related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    471
    +0.12
    0.5%
    11
    +0.11
    0.5%
    678
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    678
    +0.11
    0.03
    289
    +0.11
    0.01
    Negative Logits
    podcast
    -0.94
    soDeliveryDate
    -0.90
    erella
    -0.79
    reviewed
    -0.78
    Featured
    -0.77
     Featured
    -0.74
    Gender
    -0.73
     Saints
    -0.72
    uesday
    -0.71
    leground
    -0.70
    POSITIVE LOGITS
     pointer
    1.21
     buffer
    1.13
     ptr
    1.12
    addr
    1.08
     buffers
    1.03
     byte
    1.03
     heap
    1.03
     bytes
    1.03
     sizeof
    1.00
    buffer
    1.00
    Activations Density 0.126%

    No Known Activations