© 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. 8-RES-JB
    11. 24430
    Prev
    Next
    INDEX
    Explanations

    details about different geographic locations.

    oai_token-act-pair · gpt-3.5-turbo

    references to locations and physical descriptions of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     positives
    -0.66
    rists
    -0.65
    aughs
    -0.61
    selves
    -0.59
     Flavoring
    -0.58
    olicited
    -0.57
    isode
    -0.57
     awa
    -0.57
     Conversation
    -0.56
    £ı
    -0.56
    POSITIVE LOGITS
     suburb
    1.08
     limestone
    0.89
     overlooking
    0.81
     rented
    0.79
     parish
    0.79
     adjoining
    0.78
     farmland
    0.78
     northwest
    0.78
     leased
    0.77
     township
    0.77
    Activations Density 0.782%

    No Known Activations