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. 1659
    Prev
    Next
    INDEX
    Explanations

    financial terms and topics

    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
    488
    +0.12
    0.5%
    35
    +0.10
    0.4%
    744
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.12
    0.11
    35
    +0.10
    0.08
    66
    +0.09
    0.09
    Negative Logits
     mosqu
    -0.81
    spect
    -0.75
    natureconservancy
    -0.73
     Technique
    -0.69
     Forums
    -0.68
    unin
    -0.68
    ipolar
    -0.67
     VIDEOS
    -0.67
    heastern
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
    POSITIVE LOGITS
     payable
    1.75
     reimburse
    1.55
     royalties
    1.53
     payments
    1.51
     ($
    1.50
     (£
    1.50
     fees
    1.49
     reimbursement
    1.47
     repayment
    1.46
     payment
    1.46
    Activations Density 2.545%

    No Known Activations