© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21023
    Prev
    Next
    INDEX
    Explanations

    text related to posting content online and engaging in online discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to posts, requests, or inquiries related to various topics, especially in the context of sharing information, events, and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     looph
    -0.65
     wedd
    -0.61
    utsche
    -0.59
    ofi
    -0.58
    ueless
    -0.57
    AME
    -0.56
    idable
    -0.55
     repud
    -0.55
    atories
    -0.53
    DragonMagazine
    -0.53
    POSITIVE LOGITS
     or
    1.03
    .?
    1.00
     please
    0.99
     lately
    0.97
    please
    0.95
     :(
    0.94
     PLEASE
    0.90
     Please
    0.87
     Recently
    0.87
    /?
    0.84
    Activations Density 0.593%

    No Known Activations