© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22523
    Prev
    Next
    INDEX
    Explanations

    negation and references to fictional or non-canonical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.03
    3:0.11
    4:0.04
    5:0.09
    6:0.03
    7:0.09
    8:0.32
    9:0.02
    10:0.05
    11:0.06
    Negative Logits
     Newfoundland
    -3.94
     Lange
    -3.90
     Dartmouth
    -3.65
     Halifax
    -3.62
     McGill
    -3.62
     Hartford
    -3.61
     Lieberman
    -3.31
     Lowell
    -3.29
     Massachusetts
    -3.29
     Connecticut
    -3.27
    POSITIVE LOGITS
     Gly
    3.56
    wy
    3.40
     Cavs
    3.32
     dragon
    3.23
     dragons
    3.14
     summon
    3.11
     Summoner
    3.09
     Wizards
    3.06
     Pokemon
    3.03
     glyph
    3.00
    Activations Density 0.000%

    No Known Activations