© 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. 11-RES-JB
    11. 10079
    Prev
    Next
    INDEX
    Explanations

    mentions or discussions about the use of force, weapons, or techniques in various contexts, particularly related to law enforcement and government actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the use of force and tactics, particularly in law enforcement contexts

    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
    llah
    -0.74
    biz
    -0.68
     Adin
    -0.65
    watching
    -0.65
    orld
    -0.65
    enment
    -0.62
    si
    -0.61
    Reading
    -0.60
    wic
    -0.60
     realizes
    -0.60
    POSITIVE LOGITS
     force
    1.15
     eminent
    1.10
     coercive
    1.02
     coercion
    0.97
     taxpayer
    0.97
     leverage
    0.94
     intimidation
    0.93
     discretion
    0.92
     brute
    0.91
     aliases
    0.90
    Activations Density 0.136%

    No Known Activations