© 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. 21837
    Prev
    Next
    INDEX
    Explanations

    terms related to authority figures or institutions, particularly those involving the term "warden."

    oai_token-act-pair · gpt-3.5-turbo

    the word "warden" in various contexts, specifically focusing on its use as a title or role

    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
    awaru
    -0.72
    psc
    -0.70
    ched
    -0.69
    oric
    -0.65
     downed
    -0.65
    rupulous
    -0.64
     favour
    -0.62
     abnormal
    -0.61
     inflated
    -0.61
    ioned
    -0.59
    POSITIVE LOGITS
    arden
    1.31
    velt
    0.92
    DragonMagazine
    0.88
    esis
    0.87
    bats
    0.86
    holm
    0.83
    furt
    0.82
    stad
    0.79
    cest
    0.75
    stein
    0.75
    Activations Density 0.004%

    No Known Activations