© 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. 10-RES-JB
    11. 19059
    Prev
    Next
    INDEX
    Explanations

    occasions or events where someone speaks publicly

    oai_token-act-pair · gpt-3.5-turbo

    references to speeches and speaking engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.74
    ccording
    -0.67
    rw
    -0.66
     crept
    -0.65
     instinct
    -0.63
    ontent
    -0.61
     dens
    -0.60
    nel
    -0.60
    metics
    -0.59
     porous
    -0.59
    POSITIVE LOGITS
     onstage
    1.45
     keynote
    1.41
     lecture
    1.14
     speeches
    1.14
     speech
    1.04
     lectures
    1.03
     lect
    1.02
     podium
    1.00
     Lect
    1.00
     speakers
    0.99
    Activations Density 0.245%

    No Known Activations