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

    Neuronpedia

    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. 7-RES-JB
    11. 13653
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ALS"

    oai_token-act-pair · gpt-3.5-turbo

    references to ailments or conditions, particularly those associated with the acronym "ALS."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.94
    \\\\\\\\
    -0.86
    leness
    -0.80
    zee
    -0.77
    hold
    -0.76
    REP
    -0.75
    LY
    -0.74
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.72
    olicy
    -0.72
    rompt
    -0.70
    POSITIVE LOGITS
    anguage
    1.06
    arial
    1.04
    axy
    1.01
    urgical
    0.99
    ipop
    0.95
    pha
    0.94
    ogical
    0.94
    mith
    0.92
    icum
    0.90
    aries
    0.89
    Activations Density 0.065%

    No Known Activations