© 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. 11340
    Prev
    Next
    INDEX
    Explanations

    locations or places where people are situated or activities take place

    oai_token-act-pair · gpt-3.5-turbo

    terms related to living locations or residency

    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
     convol
    -0.68
     Contra
    -0.63
    ãĥ´ãĤ¡
    -0.62
     Malone
    -0.61
    thora
    -0.56
    rame
    -0.55
     Beats
    -0.55
    ppings
    -0.54
     Jackets
    -0.53
    chrome
    -0.53
    POSITIVE LOGITS
     congreg
    0.84
     geographically
    0.80
     resides
    0.79
    %:
    0.78
    ezvous
    0.74
    ,.
    0.73
    abouts
    0.72
     reside
    0.70
    /,
    0.70
     resided
    0.68
    Activations Density 0.110%

    No Known Activations