© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 17082
    Prev
    Next
    INDEX
    Explanations

    sports matches or events with one team or player against another

    oai_token-act-pair · gpt-3.5-turbo

    references to competitive matchups or pairings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    shire
    -0.83
    collar
    -0.79
    wcs
    -0.74
     liner
    -0.70
    spot
    -0.68
    olitan
    -0.66
    MER
    -0.66
    oola
    -0.66
    illary
    -0.65
    estern
    -0.65
    POSITIVE LOGITS
    creen
    0.71
    ipers
    0.62
    apons
    0.62
    .,
    0.62
    ky
    0.61
     RHP
    0.60
    ampa
    0.59
    maxwell
    0.57
     seq
    0.57
    pecting
    0.56
    Activations Density 0.011%

    No Known Activations