© 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 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. 2-RES-JB
    11. 15810
    Prev
    Next
    INDEX
    Explanations

    cities in the United States

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of place names, specifically cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orst
    -0.91
    lihood
    -0.79
    hart
    -0.77
    alf
    -0.77
    ogens
    -0.76
    ird
    -0.75
    ardi
    -0.73
    én
    -0.72
    rodu
    -0.72
    andr
    -0.70
    POSITIVE LOGITS
     skyline
    0.89
     Raleigh
    0.82
     Niagara
    0.81
     Cincinnati
    0.78
     Chattanooga
    0.77
    urses
    0.77
     mosqu
    0.76
     mayoral
    0.75
     Wilmington
    0.75
     Rochester
    0.74
    Activations Density 0.015%

    No Known Activations