Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 1777
    Prev
    Next
    INDEX
    Explanations

    Twitter handles and email addresses

    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
    124
    +0.13
    0.6%
    371
    +0.12
    0.5%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.13
    0.04
    627
    +0.12
    0.03
    176
    +0.11
    0.03
    Negative Logits
     distribut
    -0.69
     Inferno
    -0.67
     Elephant
    -0.65
     descend
    -0.63
     deflation
    -0.62
     Tac
    -0.61
     scoop
    -0.61
     Corruption
    -0.61
     Proced
    -0.60
     Lent
    -0.60
    POSITIVE LOGITS
    gmail
    1.64
    #$
    1.37
    yahoo
    1.26
    home
    1.12
    realDonaldTrump
    1.11
    example
    1.06
    localhost
    0.99
    bleacher
    0.98
    gnu
    0.98
    lists
    0.97
    Activations Density 0.173%

    No Known Activations