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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 14791
    Prev
    Next
    INDEX
    Explanations

    keyword phrases related to a specific game strategy involving summoning monsters from the graveyard to create powerful combinations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to summoning and managing game mechanics for monsters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gee
    -0.79
     eas
    -0.74
     blat
    -0.73
    iatus
    -0.72
     circumcision
    -0.69
     todd
    -0.65
    Minecraft
    -0.65
    eston
    -0.63
    Reviewer
    -0.60
     saf
    -0.60
    POSITIVE LOGITS
     CARD
    0.97
     Summon
    0.86
     ATK
    0.85
     Spell
    0.84
     [(
    0.84
     summoned
    0.81
     Fusion
    0.81
     Pend
    0.81
     discard
    0.78
     Equip
    0.78
    Activations Density 0.074%

    No Known Activations