© 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. 10-RES-JB
    11. 18848
    Prev
    Next
    INDEX
    Explanations

    locations in Syria, particularly related to political or military events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and geographical areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kinson
    -0.85
    ritz
    -0.71
    obin
    -0.70
    kefeller
    -0.67
    olini
    -0.67
    ellow
    -0.66
    olics
    -0.66
    inelli
    -0.64
    otti
    -0.62
    thood
    -0.61
    POSITIVE LOGITS
    س
    0.75
     Idlib
    0.74
    د
    0.73
    ById
    0.72
    Ö¼
    0.72
    ignty
    0.71
    esh
    0.70
    Rah
    0.67
    Claim
    0.66
     Emirates
    0.66
    Activations Density 0.068%

    No Known Activations