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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 7758
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific card game, likely Magic: The Gathering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming mechanics and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HIP
    -0.80
    çͰ
    -0.79
    amba
    -0.74
     Philips
    -0.74
     Rodrig
    -0.74
    apo
    -0.73
    achelor
    -0.73
    taboola
    -0.73
    rahim
    -0.69
    Þ
    -0.69
    POSITIVE LOGITS
     decks
    1.34
     mana
    1.22
     cards
    1.21
     Spells
    1.09
     deck
    1.07
     Cards
    1.04
    Spell
    1.03
     spells
    1.03
     Mana
    1.03
     Spell
    1.02
    Activations Density 0.219%

    No Known Activations