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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24572
    Prev
    Next
    INDEX
    Explanations

    Pokémon-related words, especially related to specific cards and characters

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to Pokémon, particularly specific characters and gameplay mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -1.04
     staffed
    -0.80
     actionGroup
    -0.79
    SPONSORED
    -0.78
     Ans
    -0.74
     Bohem
    -0.74
    EngineDebug
    -0.72
    espie
    -0.72
     staffing
    -0.69
     Mahm
    -0.68
    POSITIVE LOGITS
     Pikachu
    1.27
     Poké
    1.18
    Dex
    1.13
     Pokémon
    1.12
    Pokémon
    1.10
     Pokemon
    1.04
    Pokemon
    1.00
     Misty
    0.97
    oké
    0.90
    Mega
    0.90
    Activations Density 0.111%

    No Known Activations