© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 1683
    Prev
    Next
    INDEX
    Explanations

    locations or cities, specifically focusing on San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    references to San Francisco

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.83
    hift
    -0.79
    onut
    -0.74
    ãĥŀ
    -0.73
    ãĥł
    -0.73
    ror
    -0.70
     Beir
    -0.69
    insk
    -0.69
    bil
    -0.69
    respons
    -0.68
    POSITIVE LOGITS
     Bay
    1.12
     Chronicle
    1.00
     Examiner
    0.95
     Giants
    0.93
     Unified
    0.92
     Francisco
    0.89
     County
    0.86
     skyline
    0.83
     Harbor
    0.80
     Municipal
    0.80
    Activations Density 0.024%

    No Known Activations