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 1536
    5. 8-RES_FS1536-JB
    6. 1238
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    0.6%
    407
    +0.10
    0.5%
    685
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.12
    0.12
    35
    +0.10
    0.08
    268
    +0.10
    0.05
    Negative Logits
    spect
    -0.78
    natureconservancy
    -0.75
     mosqu
    -0.74
    uder
    -0.70
     Technique
    -0.70
    Temperature
    -0.66
     VIDEOS
    -0.66
    Í
    -0.66
    hent
    -0.65
     Forums
    -0.65
    POSITIVE LOGITS
     payable
    1.66
     reimburse
    1.61
     royalties
    1.56
     payments
    1.56
     expenses
    1.50
     repayment
    1.49
     (£
    1.48
     repay
    1.48
     reimbursement
    1.46
     payment
    1.46
    Activations Density 3.813%

    No Known Activations