© 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. 9-RES-JB
    11. 22754
    Prev
    Next
    INDEX
    Explanations

    phrases related to incidents or events where someone is taken to a hospital or medical center

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "taken" in various contexts related to injury or arrest

    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
     artif
    -0.63
    iciency
    -0.62
     insurg
    -0.61
     acron
    -0.60
    ãĤ¦ãĤ¹
    -0.59
     Clicker
    -0.59
     pse
    -0.58
     beginnings
    -0.58
    plays
    -0.58
     stripe
    -0.58
    POSITIVE LOGITS
     handcuffed
    0.93
     medically
    0.89
     prisoner
    0.86
     into
    0.86
     alive
    0.86
     onto
    0.84
    airo
    0.83
     hostage
    0.83
     captive
    0.82
     aback
    0.80
    Activations Density 0.110%

    No Known Activations