© 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. 9-RES-JB
    11. 11233
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    references to San Francisco and related entities

    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
    mble
    -0.96
    lain
    -0.88
    ijah
    -0.82
    ividual
    -0.78
    ioned
    -0.75
    hift
    -0.73
    insk
    -0.71
    ilater
    -0.70
    meal
    -0.69
    bil
    -0.69
    POSITIVE LOGITS
     Bay
    1.20
     Chronicle
    1.18
     Giants
    1.11
     Examiner
    1.00
     Unified
    0.99
     Francisco
    0.90
    Bay
    0.85
     49
    0.79
     bay
    0.79
     County
    0.78
    Activations Density 0.042%

    No Known Activations