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. 373
    Prev
    Next
    INDEX
    Explanations

    uses of quotations in textual content

    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
    314
    +0.16
    0.8%
    759
    +0.12
    0.5%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.16
    0.09
    442
    +0.12
    0.09
    157
    +0.11
    0.09
    Negative Logits
     Companion
    -0.74
     Samar
    -0.73
     Skydragon
    -0.70
     Circus
    -0.69
     ABE
    -0.67
     Hollywood
    -0.67
     MUS
    -0.66
     SPI
    -0.65
     swast
    -0.64
     Tasman
    -0.63
    POSITIVE LOGITS
    t
    1.17
    eal
    1.17
    tu
    1.12
    tre
    1.08
    vest
    1.04
    ve
    1.03
    tion
    1.03
    sent
    1.01
    ple
    1.01
    ¼
    1.00
    Activations Density 0.223%

    No Known Activations