Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11399
    Prev
    Next
    INDEX
    Explanations

    references to the city of San Francisco

    oai_token-act-pair · gpt-3.5-turbo

    mentions of San Francisco (SF)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.84
    stall
    -0.83
    taker
    -0.73
    pins
    -0.71
    berus
    -0.71
    hift
    -0.69
    abase
    -0.69
    pin
    -0.68
     Kant
    -0.67
    iasis
    -0.67
    POSITIVE LOGITS
    PD
    1.00
     Chronicle
    0.98
    WA
    0.97
    SF
    0.94
    ML
    0.92
    ORE
    0.91
    DC
    0.91
    ORTS
    0.90
    WD
    0.89
    DF
    0.88
    Activations Density 0.010%

    No Known Activations