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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20951
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement actions, specifically arrests

    oai_token-act-pair · gpt-3.5-turbo

    references to arrests and legal charges

    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
    emonic
    -0.63
    edge
    -0.63
    issance
    -0.62
     opin
    -0.61
    dust
    -0.60
    DragonMagazine
    -0.59
    profits
    -0.59
    ichever
    -0.59
    phies
    -0.59
    rats
    -0.58
    POSITIVE LOGITS
     by
    0.81
     overnight
    0.79
     shortly
    0.79
     alongside
    0.78
     pending
    0.77
     handcuffed
    0.74
     protesting
    0.74
     for
    0.73
     criminally
    0.72
     along
    0.71
    Activations Density 0.076%

    No Known Activations