© 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. 9-RES-JB
    11. 10370
    Prev
    Next
    INDEX
    Explanations

    ways to improve or contribute to something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of making something better or improving it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xus
    -0.75
    orsi
    -0.67
    lihood
    -0.66
    isks
    -0.65
    pta
    -0.64
    plings
    -0.64
    76561
    -0.63
    been
    -0.63
    bryce
    -0.63
     reserves
    -0.62
    POSITIVE LOGITS
     happen
    1.12
     disappear
    0.99
     worthwhile
    0.96
     believable
    0.96
     manageable
    0.93
     easier
    0.92
     sustainable
    0.89
     habitable
    0.89
     accessible
    0.88
     smoother
    0.88
    Activations Density 0.125%

    No Known Activations