© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 7830
    Prev
    Next
    INDEX
    Explanations

    mentions of Nobel Prizes and related terms, such as laureates and winners

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Nobel Prizes and laureates

    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
     Aber
    -0.73
    src
    -0.73
    mson
    -0.70
     Sega
    -0.70
    HUD
    -0.65
    anwhile
    -0.64
    alter
    -0.62
    rome
    -0.62
    okemon
    -0.61
     Antar
    -0.61
    POSITIVE LOGITS
     Prize
    1.72
     laureate
    1.58
     laure
    1.30
     Laure
    1.22
    Pri
    1.19
     prize
    1.16
    Nob
    1.08
     Award
    1.04
     pri
    0.99
     Pri
    0.97
    Activations Density 0.037%

    No Known Activations