© 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 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. 6-RES-JB
    11. 14649
    Prev
    Next
    INDEX
    Explanations

    phrases related to card decks in games

    oai_token-act-pair · gpt-3.5-turbo

    references to decks in card games

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heric
    -0.77
    phrine
    -0.73
    çīĪ
    -0.72
    interstitial
    -0.69
     satellites
    -0.64
    ipient
    -0.64
    ternity
    -0.64
    alties
    -0.62
    Downloadha
    -0.61
     cessation
    -0.60
    POSITIVE LOGITS
    lists
    1.35
    builder
    1.05
    list
    1.04
    igans
    1.02
    igan
    0.93
    mates
    0.92
    strap
    0.92
     deck
    0.88
    nut
    0.88
    building
    0.88
    Activations Density 0.021%

    No Known Activations