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 3072
    5. 8-RES_FS3072-JB
    6. 479
    Prev
    Next
    INDEX
    Explanations

    amounts of money

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    352
    +0.10
    0.5%
    488
    +0.10
    0.5%
    542
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.10
    0.08
    352
    +0.10
    0.09
    310
    +0.10
    0.08
    Negative Logits
    soType
    -0.67
    reason
    -0.62
    iths
    -0.62
    iders
    -0.61
     Metatron
    -0.60
    isers
    -0.58
    umbn
    -0.58
    alys
    -0.58
    ãĥĥãĥī
    -0.58
    aple
    -0.57
    POSITIVE LOGITS
    -$
    1.41
     (£
    1.26
     apiece
    1.18
    /$
    1.16
     USD
    1.14
     ($
    1.05
     annually
    1.00
     dollars
    0.98
     worth
    0.96
    USD
    0.95
    Activations Density 0.510%

    No Known Activations