© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 21973
    Prev
    Next
    INDEX
    Explanations

    references to physical screens or projections

    oai_token-act-pair · gpt-3.5-turbo

    references to screens used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sen
    -0.71
    Ton
    -0.67
    ETA
    -0.66
    ETH
    -0.64
    neg
    -0.63
     Coch
    -0.63
     homicide
    -0.62
    Contribut
    -0.62
    iev
    -0.61
    GAN
    -0.61
    POSITIVE LOGITS
     screens
    1.54
     screen
    1.07
    creen
    1.05
     TVs
    1.00
    reens
    0.97
    pring
    0.95
     screenings
    0.90
    avers
    0.89
    plays
    0.88
     wallpaper
    0.86
    Activations Density 0.004%

    No Known Activations