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. 19043
    Prev
    Next
    INDEX
    Explanations

    information related to various news events and incidents

    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
    481
    +0.24
    1.1%
    383
    +0.09
    0.4%
    610
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.24
    0.06
    698
    +0.09
    0.05
    762
    +0.09
    0.06
    Negative Logits
     inaction
    -0.63
     presumption
    -0.61
    Reviewer
    -0.60
     IPM
    -0.59
    addons
    -0.58
    ERC
    -0.58
     committees
    -0.56
    essor
    -0.56
    Term
    -0.56
    IPS
    -0.54
    POSITIVE LOGITS
     belonging
    0.87
     apiece
    0.87
     respectively
    0.79
     accompany
    0.79
     residing
    0.78
     accompanied
    0.78
     onboard
    0.77
     onto
    0.77
     lodged
    0.76
     attached
    0.75
    Activations Density 0.533%

    No Known Activations