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. 21760
    Prev
    Next
    INDEX
    Explanations

    words related to companies and governmental agencies

    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
    197
    +0.11
    0.5%
    534
    +0.10
    0.4%
    117
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    197
    +0.11
    0.03
    108
    +0.10
    0.03
    206
    +0.09
    0.03
    Negative Logits
    truth
    -0.70
    iverse
    -0.68
    izophren
    -0.67
    izoph
    -0.67
     mell
    -0.64
    secut
    -0.63
    zh
    -0.62
    iety
    -0.61
    amy
    -0.61
     worsen
    -0.60
    POSITIVE LOGITS
     worldwide
    0.77
     subcontract
    0.71
     Worldwide
    0.71
     products
    0.68
     outsourcing
    0.68
     licenses
    0.66
     contracts
    0.65
     servicing
    0.65
     distributed
    0.65
     weddings
    0.65
    Activations Density 0.179%

    No Known Activations