© 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. 22642
    Prev
    Next
    INDEX
    Explanations

    information related to law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo

    references to police activities or law enforcement actions

    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
    amental
    -0.71
     ALEC
    -0.70
    Works
    -0.67
    TABLE
    -0.66
     moderation
    -0.65
     whining
    -0.64
    ufact
    -0.63
    lies
    -0.62
    iscons
    -0.62
    bench
    -0.61
    POSITIVE LOGITS
     arrested
    1.20
     arrests
    1.12
     suspect
    1.06
     apprehended
    1.04
     apprehend
    1.03
     suspects
    1.02
     Detect
    1.00
     arresting
    0.99
     detained
    0.99
     nab
    0.99
    Activations Density 0.200%

    No Known Activations