© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 7943
    Prev
    Next
    INDEX
    Explanations

    references to Pokémon-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to Pokémon and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.88
    EngineDebug
    -0.74
     actionGroup
    -0.71
    amily
    -0.68
    $$
    -0.67
    itect
    -0.67
    hol
    -0.66
    ihad
    -0.66
    anticipated
    -0.66
    ©¶æ
    -0.66
    POSITIVE LOGITS
     Pikachu
    1.19
    Dex
    1.08
     Poké
    1.00
     Pokemon
    0.96
     Pokémon
    0.95
    Pokémon
    0.93
    Pokemon
    0.92
    Poké
    0.91
     Bowser
    0.87
     pokemon
    0.86
    Activations Density 0.114%

    No Known Activations