© 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. 11-RES-JB
    11. 7011
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of New York and its mayor

    oai_token-act-pair · gpt-3.5-turbo

    mentions of New York City and its mayoral context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rar
    -0.87
    yip
    -0.81
    ibility
    -0.77
    icum
    -0.75
    ãĥ¬
    -0.73
    terness
    -0.72
    riet
    -0.72
    gotten
    -0.70
    wcsstore
    -0.69
     instr
    -0.69
    POSITIVE LOGITS
     subway
    1.08
     skyline
    1.02
     Mayor
    1.01
     borough
    1.01
     FC
    0.97
     landmarks
    0.95
     sidewalks
    0.92
    scape
    0.91
     neighborhoods
    0.91
     Transit
    0.89
    Activations Density 0.062%

    No Known Activations