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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1173
    Prev
    Next
    INDEX
    Explanations

    terms related to financial aspects such as profits, revenue streams, income, and taxes

    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
    71
    +0.15
    0.7%
    496
    +0.13
    0.6%
    285
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.08
    444
    +0.13
    0.05
    285
    +0.10
    0.04
    Negative Logits
     Keller
    -0.65
    lain
    -0.65
    sonian
    -0.64
    uj
    -0.63
    opol
    -0.63
     Revision
    -0.61
     Clover
    -0.60
    oggle
    -0.60
    Berry
    -0.60
     Bolt
    -0.60
    POSITIVE LOGITS
     earners
    1.28
     income
    1.05
     earnings
    1.04
     streams
    1.00
     receipts
    0.95
     Income
    0.95
     earned
    0.94
     revenue
    0.92
     taxes
    0.91
     Taxes
    0.90
    Activations Density 0.742%

    No Known Activations