© 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. 10-RES-JB
    11. 19030
    Prev
    Next
    INDEX
    Explanations

    information or references to law enforcement activities and investigations

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to information and law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.67
     Galile
    -0.66
     Roe
    -0.65
     charism
    -0.61
     Mechdragon
    -0.61
    theless
    -0.60
     Holding
    -0.60
    hani
    -0.60
    TPPStreamerBot
    -0.59
     distingu
    -0.59
    POSITIVE LOGITS
    hered
    0.90
    arious
    0.88
    creen
    0.85
    nyder
    0.84
    aign
    0.82
     pics
    0.79
     gotta
    0.77
    zzy
    0.77
    ILS
    0.76
     ops
    0.73
    Activations Density 0.136%

    No Known Activations