© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6326
    Prev
    Next
    INDEX
    Explanations

    categories and characteristics related to species in a contest or submission context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.16
    1:0.03
    2:0.04
    3:0.09
    4:0.11
    5:0.15
    6:0.02
    7:0.13
    8:0.06
    9:0.02
    10:0.09
    11:0.03
    Negative Logits
     telev
    -2.16
    steen
    -2.11
     Consumers
    -1.94
     crim
    -1.91
     Dow
    -1.84
     manufactures
    -1.82
     Greenpeace
    -1.76
     spokes
    -1.76
     supermarket
    -1.74
    aspers
    -1.73
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    2.54
    Untitled
    2.06
    Strange
    2.04
    Ali
    2.03
    Evil
    1.91
     annotations
    1.88
    Theme
    1.88
    Subject
    1.87
    png
    1.87
     Submission
    1.86
    Activations Density 0.001%

    No Known Activations