© 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. 3525
    Prev
    Next
    INDEX
    Explanations

    URL shortening services, specifically "usat"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the USA Today news website

    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
    ©¶æ
    -0.66
     sole
    -0.56
     Colossus
    -0.55
    @#&
    -0.55
     Pir
    -0.55
    ortunately
    -0.54
     Silent
    -0.53
     Kris
    -0.53
     Gou
    -0.52
     ninety
    -0.51
    POSITIVE LOGITS
    daq
    0.98
    oday
    0.98
    natureconservancy
    0.86
    bilt
    0.75
    ascript
    0.74
    imes
    0.74
    yssey
    0.73
    imedia
    0.71
    usat
    0.70
    ebin
    0.69
    Activations Density 0.016%

    No Known Activations