© 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. 7548
    Prev
    Next
    INDEX
    Explanations

    locations in the United States

    oai_token-act-pair · gpt-3.5-turbo

    names of U.S. states and locations within them

    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
    20439
    -0.64
    road
    -0.63
     robber
    -0.59
    Afee
    -0.59
     predict
    -0.57
    mania
    -0.57
    merce
    -0.56
     Doodle
    -0.54
     Crimean
    -0.54
    peat
    -0.54
    POSITIVE LOGITS
    .,
    0.86
    ;;;;;;;;;;;;
    0.85
    soDeliveryDate
    0.75
    .;
    0.70
    ometown
    0.69
    quartered
    0.68
    ,,
    0.67
    ,...
    0.66
     native
    0.63
    nice
    0.61
    Activations Density 0.083%

    No Known Activations