© 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. 3-RES-JB
    11. 20405
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, specifically boroughs and Staten Island

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations, particularly boroughs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibaba
    -0.79
    inen
    -0.75
    TPP
    -0.70
    Downloadha
    -0.68
    cius
    -0.68
    VID
    -0.68
    positive
    -0.68
    riott
    -0.67
    ctory
    -0.67
    PLA
    -0.65
    POSITIVE LOGITS
     borough
    1.47
     Borough
    1.43
     councils
    0.94
     oun
    0.82
    mates
    0.82
     neighb
    0.81
    orough
    0.78
     Brooklyn
    0.78
    wide
    0.77
     alley
    0.76
    Activations Density 0.011%

    No Known Activations