© 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. 21079
    Prev
    Next
    INDEX
    Explanations

    names of specific locations around the world

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and proper nouns related to places

    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
    Wilson
    -0.71
    Denver
    -0.64
    idious
    -0.64
     Paige
    -0.63
    writers
    -0.62
    Jones
    -0.61
     Holly
    -0.61
    reason
    -0.60
     resil
    -0.60
     Lexington
    -0.60
    POSITIVE LOGITS
     province
    1.47
     Province
    1.44
     Municip
    1.29
     municipality
    1.21
     Airport
    1.15
     airport
    1.11
     County
    1.10
     Cathedral
    1.07
     Pradesh
    1.05
     harbour
    1.04
    Activations Density 0.228%

    No Known Activations