© 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. 3699
    Prev
    Next
    INDEX
    Explanations

    words related to hypothetical scenarios or future possibilities

    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
    763
    +0.11
    0.5%
    449
    +0.11
    0.5%
    713
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.11
    0.06
    713
    +0.11
    0.04
    551
    +0.11
    0.04
    Negative Logits
     doubts
    -0.70
    clerosis
    -0.62
    hua
    -0.60
    76561
    -0.60
     Tsuk
    -0.57
    ocent
    -0.57
    vier
    -0.56
     Medline
    -0.56
    cit
    -0.56
    engineering
    -0.56
    POSITIVE LOGITS
     entail
    1.02
     be
    0.99
     achieve
    0.85
     accomplish
    0.84
    dos
    0.82
     tolerate
    0.79
     someday
    0.78
     fare
    0.77
     unfold
    0.77
     behave
    0.77
    Activations Density 0.111%

    No Known Activations