© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 7377
    Prev
    Next
    INDEX
    Explanations

    words related to specific organizations or locations, specifically those related to a Metropolitan entity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Metropolitan" and related terminology that implies city or urban contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.86
    fty
    -0.84
    cius
    -0.77
    oward
    -0.73
    enes
    -0.72
    tty
    -0.71
    verted
    -0.71
    pport
    -0.71
    terday
    -0.71
    gotten
    -0.70
    POSITIVE LOGITS
    ropolitan
    0.97
     Statistical
    0.93
     Borough
    0.91
     Metropolitan
    0.86
     Transit
    0.84
     Transportation
    0.82
     Region
    0.81
     Police
    0.79
     Regional
    0.79
     District
    0.77
    Activations Density 0.010%

    No Known Activations