© 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. 6-RES-JB
    11. 5019
    Prev
    Next
    INDEX
    Explanations

    law enforcement-related terms and names

    oai_token-act-pair · gpt-3.5-turbo

    end-of-text markers or indicate the absence of relevant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificent
    -0.84
    ifiers
    -0.78
    ionic
    -0.76
    geries
    -0.75
    isations
    -0.74
    oon
    -0.74
    alysed
    -0.73
    atu
    -0.73
    eness
    -0.71
    rooms
    -0.71
    POSITIVE LOGITS
    uate
    0.74
    cember
    0.72
    LECT
    0.69
     Cooperative
    0.69
    bris
    0.68
    hardt
    0.68
     Credits
    0.67
     Rate
    0.66
     Virus
    0.66
     Scrolls
    0.66
    Activations Density 0.112%

    No Known Activations