© 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 49152
    9. 8-RES_FS49152-JB
    11. 25957
    Prev
    Next
    INDEX
    Explanations

    instances of the word "demand" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    321
    +0.11
    0.5%
    481
    +0.10
    0.4%
    20
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.11
    0.01
    186
    +0.10
    0.01
    210
    +0.10
    0.01
    Negative Logits
    paio
    -0.84
    =-=-=-=-
    -0.74
    secret
    -0.72
    ombs
    -0.72
    named
    -0.71
    vae
    -0.70
    regor
    -0.70
    adal
    -0.69
    laus
    -0.69
    inness
    -0.68
    POSITIVE LOGITS
    demand
    0.84
     fulfillment
    0.80
    igslist
    0.78
     Networks
    0.77
     services
    0.77
     pricing
    0.75
     VPN
    0.72
     scheduling
    0.72
     viewing
    0.71
     TV
    0.71
    Activations Density 0.009%

    No Known Activations