© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 3339
    Prev
    Next
    INDEX
    Explanations

    words related to business deals and financial transactions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    Neuron Alignment
    Index
    Value
    % of L₁
    34
    +0.13
    0.6%
    236
    +0.11
    0.5%
    224
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.13
    0.01
    236
    +0.11
    0.01
    530
    +0.10
    0.01
    Negative Logits
     disgu
    -0.80
    ologically
    -0.78
    hid
    -0.72
     dece
    -0.72
    gery
    -0.72
    beh
    -0.70
    iqueness
    -0.70
    ding
    -0.68
    oscope
    -0.68
     manif
    -0.68
    POSITIVE LOGITS
    CLOSE
    1.16
     PHOTO
    0.89
     Pacers
    0.85
     Hundreds
    0.84
     Latest
    0.81
     WATCHED
    0.80
     Skip
    0.79
     Expand
    0.78
    UTERS
    0.78
     Close
    0.78
    Activations Density 0.012%

    No Known Activations