© 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. 9-RES-JB
    11. 11206
    Prev
    Next
    INDEX
    Explanations

    events or speeches by notable figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "speaks at" followed by various locations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    irez
    -0.74
    gans
    -0.73
    chrome
    -0.72
     thri
    -0.69
    Owner
    -0.69
    potion
    -0.66
     benefited
    -0.65
    stead
    -0.64
    killers
    -0.64
    found
    -0.63
    POSITIVE LOGITS
     conferences
    1.18
     CES
    1.16
     festivals
    1.10
     halftime
    1.09
    rium
    1.08
     Cannes
    1.07
     PAX
    1.05
     SX
    1.02
     conventions
    1.00
     Celebration
    0.98
    Activations Density 0.159%

    No Known Activations