© 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. 8-RES-JB
    11. 4179
    Prev
    Next
    INDEX
    Explanations

    references to the Pokémon franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iffe
    -0.88
    heed
    -0.67
    ickson
    -0.66
    ubb
    -0.66
    EFF
    -0.66
    iller
    -0.66
    DCS
    -0.65
    perial
    -0.64
     tiss
    -0.64
    inges
    -0.64
    POSITIVE LOGITS
    Dex
    0.96
    Pokémon
    0.92
     Trainer
    0.91
     pokemon
    0.88
     Pokémon
    0.87
     Poké
    0.86
    athlon
    0.84
     Pokemon
    0.84
     Pikachu
    0.80
    Pokemon
    0.80
    Activations Density 0.044%

    No Known Activations