© 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. 11663
    Prev
    Next
    INDEX
    Explanations

    mentions of people named "Paul"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Paul."

    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
     lodge
    -0.74
    engineering
    -0.67
     tolerant
    -0.64
    cyl
    -0.62
    QUEST
    -0.62
    SPONSORED
    -0.61
     cortex
    -0.60
    PUT
    -0.58
    dayName
    -0.57
    ../
    -0.56
    POSITIVE LOGITS
    ine
    1.12
     McCartney
    1.07
    sen
    1.03
    son
    1.02
    ozo
    1.00
     Krugman
    0.96
    ieu
    0.93
     Manafort
    0.92
    sonian
    0.87
    angelo
    0.87
    Activations Density 0.039%

    No Known Activations