© 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. 5554
    Prev
    Next
    INDEX
    Explanations

    words related to providing information or a summary of information such as "briefing"

    oai_token-act-pair · gpt-3.5-turbo

    references to briefings and related discussions

    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
    relative
    -0.70
    adia
    -0.67
    alde
    -0.62
    negie
    -0.61
    aden
    -0.61
    breeding
    -0.60
     adultery
    -0.59
    adic
    -0.59
     Jericho
    -0.57
    morph
    -0.57
    POSITIVE LOGITS
     briefings
    1.14
     briefing
    1.02
     briefs
    0.81
     sessions
    0.77
    mares
    0.76
    urations
    0.75
     Papers
    0.73
     presentations
    0.73
    ariat
    0.72
     attendees
    0.72
    Activations Density 0.023%

    No Known Activations