© 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. 0-RES-JB
    11. 6554
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographical locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regions or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fame
    -0.78
    ict
    -0.75
     farewell
    -0.65
     Machina
    -0.64
    opus
    -0.64
    inus
    -0.64
     apiece
    -0.64
    ente
    -0.64
    actionDate
    -0.63
    writer
    -0.63
    POSITIVE LOGITS
     areas
    3.61
     Areas
    2.88
     area
    2.34
     regions
    2.15
     zones
    2.06
     sectors
    1.74
     locations
    1.72
     Area
    1.72
     sections
    1.70
     neighborhoods
    1.69
    Activations Density 0.016%

    No Known Activations