© 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. 12-RES-JB
    11. 3337
    Prev
    Next
    INDEX
    Explanations

    Japanese names, potentially with a mix of first names, surnames, and honorifics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of individuals related to anime or Japanese cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sterling
    -0.65
     Rove
    -0.62
     McKenna
    -0.60
     Cro
    -0.59
     Gret
    -0.58
     Cox
    -0.58
     Colomb
    -0.58
     Merc
    -0.58
     Camb
    -0.58
     Juliet
    -0.58
    POSITIVE LOGITS
    oka
    1.28
    uchi
    1.27
    ishi
    1.27
    awa
    1.07
    ikawa
    1.06
    oÄŁ
    1.03
    jri
    1.00
    emi
    0.97
    hiro
    0.97
    ushima
    0.95
    Activations Density 0.155%

    No Known Activations