© 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. 4-RES-JB
    11. 16810
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "Pokemon" and related terms like "Poke" and "Pokeball"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pokémon franchise and related gaming systems

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

    No Comments

    Negative Logits
    ered
    -0.82
    shire
    -0.79
    cens
    -0.72
    ding
    -0.71
    enance
    -0.70
    ufact
    -0.69
    éļ
    -0.67
    )=(
    -0.67
    ITED
    -0.66
    Topic
    -0.65
    POSITIVE LOGITS
    okemon
    1.04
    veyard
    0.94
     Pok
    0.86
    uana
    0.82
    ongyang
    0.81
     pokemon
    0.81
    ipers
    0.76
    merga
    0.76
    otle
    0.75
    ipe
    0.74
    Activations Density 0.015%

    No Known Activations