© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 17312
    Prev
    Next
    INDEX
    Explanations

    words related to different card games

    oai_token-act-pair · gpt-3.5-turbo

    terms related to game mechanics and card interactions

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

    No Comments

    Negative Logits
    enegger
    -0.85
     APP
    -0.80
     migrant
    -0.75
     UNCLASSIFIED
    -0.74
    çīĪ
    -0.73
    Þ
    -0.73
    æ©
    -0.71
     radio
    -0.70
     mosqu
    -0.70
     supervised
    -0.69
    POSITIVE LOGITS
    blade
    1.17
    mage
    1.10
    Spell
    1.08
    romancer
    1.08
    sword
    1.01
     Vengeance
    0.99
     mages
    0.99
     Aether
    0.98
     enchantment
    0.98
    forge
    0.96
    Activations Density 0.221%

    No Known Activations