© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2707
    Prev
    Next
    INDEX
    Explanations

    metaphorical language related to strategy games

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    strategic components and mechanics related to card games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olitan
    -0.90
    ä¹ĭ
    -0.89
    iatus
    -0.78
    ¨
    -0.73
    ateur
    -0.73
    ão
    -0.72
    çĶ°
    -0.72
     Weiner
    -0.72
    enegger
    -0.71
    ãĥ¼ãĤ¯
    -0.71
    POSITIVE LOGITS
     creatures
    1.23
     mana
    1.23
     creature
    1.18
     landfall
    1.14
     enchantment
    1.12
     Planes
    1.12
     Jace
    1.12
     sorcery
    1.09
     blockers
    1.07
     haste
    1.07
    Activations Density 0.151%

    No Known Activations