© 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 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. 2-RES-JB
    11. 423
    Prev
    Next
    INDEX
    Explanations

    Japanese names or words

    oai_token-act-pair · gpt-4-turbo

    character names and potentially related terms or themes from a specific franchise or series

    oai_token-act-pair · gpt-3.5-turbo

    references to Japanese anime and its creators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    espie
    -0.91
    Colorado
    -0.74
    tackle
    -0.73
     turf
    -0.72
    vantage
    -0.70
     Lyme
    -0.69
    trace
    -0.69
     carc
    -0.69
    Reviewer
    -0.68
    cro
    -0.68
    POSITIVE LOGITS
     Manga
    1.23
     Yen
    1.13
     manga
    1.09
     Yamato
    1.07
     Tanaka
    1.07
    ichi
    1.07
    jin
    1.07
     Rin
    1.06
     Yosh
    1.05
     Ryu
    1.04
    Activations Density 0.251%

    No Known Activations