© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 20899
    Prev
    Next
    INDEX
    Explanations

    law enforcement-related terms, particularly mentioning "deputies"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of law enforcement officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.86
    FORE
    -0.84
    ces
    -0.76
    ¥µ
    -0.75
    hetti
    -0.73
    drive
    -0.71
    gged
    -0.71
    eb
    -0.70
    church
    -0.70
    Virgin
    -0.69
    POSITIVE LOGITS
     deputies
    1.18
     confir
    1.01
     sheriff
    0.89
    uty
    0.87
    uties
    0.84
     sher
    0.83
    ixel
    0.79
     handlers
    0.78
     detained
    0.76
     dispatcher
    0.74
    Activations Density 0.008%

    No Known Activations