Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19265
    Prev
    Next
    INDEX
    Explanations

    references to anime and video game titles, especially related to the Gundam and Naruto series

    oai_token-act-pair · gpt-3.5-turbo

    references to anime titles and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sten
    -0.81
    oway
    -0.80
    oller
    -0.77
    Ö¼
    -0.75
    riers
    -0.73
    send
    -0.72
    reys
    -0.71
    rors
    -0.70
    leneck
    -0.69
    oley
    -0.68
    POSITIVE LOGITS
     Gundam
    0.94
     Yamato
    0.89
     Goku
    0.87
    earances
    0.83
     Piece
    0.82
     Korra
    0.81
     Luffy
    0.80
    ikuman
    0.79
     Tsukuyomi
    0.78
     Naruto
    0.77
    Activations Density 0.020%

    No Known Activations