© 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. 4-RES-JB
    11. 7242
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement officers with the title Sheriff

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement officials or the term "Sheriff"

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

    No Comments

    Negative Logits
    lihood
    -0.88
    jad
    -0.79
    ted
    -0.77
    ankind
    -0.70
    yip
    -0.69
    76561
    -0.66
     Centauri
    -0.65
    ctory
    -0.64
    umar
    -0.63
    ptions
    -0.63
    POSITIVE LOGITS
     Sheriff
    1.03
     sheriff
    1.01
    osate
    0.83
     commissioner
    0.81
     Marshal
    0.80
     coroner
    0.77
    Sher
    0.75
     deputies
    0.75
    icio
    0.73
    iffs
    0.72
    Activations Density 0.011%

    No Known Activations