© 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. 11-RES-JB
    11. 6098
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations, specifically neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    references to neighborhoods and their characteristics

    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
    ulum
    -0.88
    inen
    -0.82
    xon
    -0.76
    anson
    -0.76
    argon
    -0.75
    uid
    -0.75
    zers
    -0.75
    swer
    -0.74
    irection
    -0.74
    estamp
    -0.74
    POSITIVE LOGITS
     grocer
    0.99
     neighbourhood
    0.98
     neighborhood
    0.97
     neighborhoods
    0.96
     Neighborhood
    0.92
     synagogue
    0.88
     Neigh
    0.86
     neighbourhoods
    0.86
     streets
    0.85
     borough
    0.84
    Activations Density 0.072%

    No Known Activations