© 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. 10-RES-JB
    11. 18670
    Prev
    Next
    INDEX
    Explanations

    phrases or titles containing the abbreviation "Sgt" followed by a period

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement personnel, specifically sergeants

    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
    ahime
    -0.83
    FML
    -0.77
     largeDownload
    -0.72
    rights
    -0.67
     feminism
    -0.67
     divest
    -0.65
     veiled
    -0.65
     temples
    -0.65
     embargo
    -0.65
     sway
    -0.64
    POSITIVE LOGITS
     Sgt
    1.27
     Sergeant
    1.21
    geant
    1.16
     Constable
    1.05
     Pepper
    1.00
    gt
    0.97
     Brian
    0.97
     Maj
    0.97
    atton
    0.96
     Keith
    0.96
    Activations Density 0.050%

    No Known Activations