© 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 EvalsExportsAPI 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. 8-RES-JB
    11. 19378
    Prev
    Next
    INDEX
    Explanations

    news articles from Reuters related to global events

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and related punctuation in news reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irlf
    -0.64
     Exhibition
    -0.61
    req
    -0.60
     Stall
    -0.57
    course
    -0.56
     Sims
    -0.56
     spoiler
    -0.55
     undergrad
    -0.55
    bage
    -0.54
     trophies
    -0.54
    POSITIVE LOGITS
    eka
    0.77
    Reuters
    0.72
     WORLD
    0.66
     Kurdistan
    0.65
     sidx
    0.64
    everal
    0.64
     WATCHED
    0.62
    heast
    0.61
    ccording
    0.61
    ANCE
    0.61
    Activations Density 0.039%

    No Known Activations