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. 458
    Prev
    Next
    INDEX
    Explanations

    mentions of financial terms and transactions

    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
    534
    +0.12
    0.6%
    362
    +0.12
    0.5%
    572
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.13
    572
    +0.12
    0.10
    534
    +0.09
    0.07
    Negative Logits
    reci
    -0.82
    accompan
    -0.77
    Synopsis
    -0.75
    headers
    -0.72
     relate
    -0.70
    ãĤ¦ãĤ¹
    -0.69
    aucuses
    -0.69
    TEXT
    -0.68
    pmwiki
    -0.68
    userc
    -0.67
    POSITIVE LOGITS
     Xer
    0.92
     Greenpeace
    0.91
     Cornell
    0.91
     Carnegie
    0.91
     Nex
    0.90
     Ubisoft
    0.90
     Mozilla
    0.90
     Purdue
    0.89
     Microsoft
    0.88
     Georgetown
    0.88
    Activations Density 1.597%

    No Known Activations