© 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. 12336
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement personnel and ranks

    oai_token-act-pair · gpt-3.5-turbo

    references to ranks and titles in law enforcement

    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
     largeDownload
    -0.77
     dormant
    -0.69
     favourable
    -0.68
    ESE
    -0.65
     coincide
    -0.65
    ahime
    -0.65
     whims
    -0.64
    nis
    -0.64
    FML
    -0.63
     absor
    -0.63
    POSITIVE LOGITS
     Sgt
    1.49
     Sergeant
    1.19
     Trooper
    1.14
     Brian
    1.13
     Darren
    1.12
     Keith
    1.09
    geant
    1.08
     Garry
    1.08
     Javier
    1.06
     Jason
    1.06
    Activations Density 0.073%

    No Known Activations