© 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. 1-RES-JB
    11. 22622
    Prev
    Next
    INDEX
    Explanations

    words related to the title or position of a sheriff

    oai_token-act-pair · gpt-3.5-turbo

    references to sheriffs or law enforcement figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.68
     CAD
    -0.66
     rotating
    -0.63
    76561
    -0.63
     WikiLeaks
    -0.63
     Wikileaks
    -0.62
     Origin
    -0.62
    tar
    -0.61
     Phi
    -0.61
     Elon
    -0.60
    POSITIVE LOGITS
    Sher
    1.37
    idan
    0.92
    mallow
    0.90
    iff
    0.88
    lock
    0.87
    icio
    0.87
    itans
    0.84
    ald
    0.80
    atures
    0.78
    abel
    0.77
    Activations Density 0.006%

    No Known Activations