© 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. 24561
    Prev
    Next
    INDEX
    Explanations

    references to images or photographs within the text

    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
    0:0.04
    1:0.04
    2:0.02
    3:0.05
    4:0.13
    5:0.04
    6:0.25
    7:0.05
    8:0.20
    9:0.04
    10:0.08
    11:0.01
    Negative Logits
     Malays
    -4.39
     Icelandic
    -4.06
     Thai
    -3.96
     monkeys
    -3.94
     Iceland
    -3.83
     Canary
    -3.80
     Emirates
    -3.75
     apes
    -3.69
     Dolphin
    -3.60
     tigers
    -3.53
    POSITIVE LOGITS
    Michigan
    4.78
     Lansing
    4.05
    Buy
    4.03
    CLOSE
    3.94
    aukee
    3.93
    agin
    3.58
     Michigan
    3.56
     Township
    3.51
    Wisconsin
    3.50
    Indiana
    3.50
    Activations Density 0.002%

    No Known Activations