© 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. 8-RES-JB
    11. 24382
    Prev
    Next
    INDEX
    Explanations

    events or actions occurring shortly before a specific date or event

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating occurrences leading up to significant events

    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
    esian
    -0.73
    ragon
    -0.70
    drivers
    -0.70
    isms
    -0.68
    ãĤ¤
    -0.66
    arta
    -0.64
    owan
    -0.63
    atile
    -0.63
    RW
    -0.63
    ged
    -0.62
    POSITIVE LOGITS
     Christmas
    1.08
     Thanksgiving
    1.00
     sunrise
    0.96
     noon
    0.93
     kickoff
    0.89
     midnight
    0.89
     sunset
    0.83
     Election
    0.82
     Halloween
    0.80
     scheduled
    0.80
    Activations Density 0.054%

    No Known Activations