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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1742
    Prev
    Next
    INDEX
    Explanations

    terms related to financial crisis and debt

    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
    459
    +0.13
    0.6%
    285
    +0.10
    0.5%
    195
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.07
    352
    +0.10
    0.05
    459
    +0.10
    0.05
    Negative Logits
    advertising
    -0.83
    £ı
    -0.82
    Ĥ¬
    -0.78
    oute
    -0.71
    Ale
    -0.71
    GMT
    -0.70
    lymp
    -0.70
    stasy
    -0.68
    Ͻ
    -0.66
    é¾
    -0.66
    POSITIVE LOGITS
     repayment
    1.44
     repay
    1.33
     debt
    1.16
     forgiveness
    1.12
     incurred
    1.09
     repaid
    1.08
     owed
    1.02
     debts
    0.98
     borrowers
    0.97
     Debt
    0.97
    Activations Density 0.718%

    No Known Activations