© 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. 9-RES-JB
    11. 4625
    Prev
    Next
    INDEX
    Explanations

    email-related prompts asking the user to confirm they are not a robot

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods

    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
    âĢİ
    -0.80
     lamb
    -0.67
    kaya
    -0.65
     tact
    -0.65
     oun
    -0.63
     consistency
    -0.62
    imer
    -0.61
    ouf
    -0.61
     way
    -0.60
     boycot
    -0.60
    POSITIVE LOGITS
     Invalid
    1.10
     Please
    0.80
    Submit
    0.77
    google
    0.77
    php
    0.73
     Thumbnails
    0.68
     transcription
    0.68
    VERT
    0.68
    Pocket
    0.66
    browser
    0.66
    Activations Density 0.031%

    No Known Activations