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. 23458
    Prev
    Next
    INDEX
    Explanations

    words related to teaching and learning opportunities

    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
    447
    +0.15
    0.7%
    58
    +0.12
    0.5%
    67
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.15
    0.04
    58
    +0.12
    0.04
    671
    +0.10
    0.04
    Negative Logits
    rather
    -0.75
     [&
    -0.67
    itton
    -0.63
    pmwiki
    -0.63
    Hope
    -0.61
    LOS
    -0.60
    hai
    -0.58
    ingen
    -0.57
    truth
    -0.57
    hey
    -0.57
    POSITIVE LOGITS
     nor
    1.59
     anymore
    1.55
     any
    1.18
     anything
    1.14
     anybody
    1.04
     necessarily
    1.02
     anywhere
    1.00
     whatsoever
    0.97
     anyone
    0.97
     slightest
    0.95
    Activations Density 0.535%

    No Known Activations