© 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. 11-RES-JB
    11. 9442
    Prev
    Next
    INDEX
    Explanations

    locations and places in China

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear power plants in specific geographic locations

    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
     msec
    -0.70
    iott
    -0.65
    TOR
    -0.65
     Brees
    -0.64
    Cass
    -0.64
     Ares
    -0.63
    ̶
    -0.63
     cows
    -0.61
     calves
    -0.60
    ById
    -0.60
    POSITIVE LOGITS
    jiang
    1.52
    hai
    1.30
    zhou
    1.25
    jing
    1.20
     Province
    1.19
     Zhu
    1.14
     Jiang
    1.14
    xia
    1.13
    xi
    1.12
    hua
    1.11
    Activations Density 0.111%

    No Known Activations