© 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. 10552
    Prev
    Next
    INDEX
    Explanations

    phrases related to card games and strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to card games, particularly actions and effects involving cards

    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
     redes
    -0.80
    indust
    -0.74
    Asia
    -0.74
     Philips
    -0.70
     discontin
    -0.70
     HIP
    -0.69
     corpor
    -0.68
     Degree
    -0.68
    aternity
    -0.67
     differe
    -0.67
    POSITIVE LOGITS
     mana
    1.04
     aggro
    1.01
     combos
    0.99
     combo
    0.96
     Spells
    0.94
     Mana
    0.91
    onent
    0.88
     Paladin
    0.87
     minions
    0.87
    brainer
    0.86
    Activations Density 0.219%

    No Known Activations