© 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. 13677
    Prev
    Next
    INDEX
    Explanations

    mentions of digital communication and online content, specifically related to support or resources

    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
    0:0.06
    1:0.04
    2:0.05
    3:0.03
    4:0.07
    5:0.04
    6:0.16
    7:0.05
    8:0.11
    9:0.28
    10:0.02
    11:0.05
    Negative Logits
     trout
    -3.74
     Baal
    -3.54
    anyahu
    -3.45
    rb
    -3.42
    callback
    -3.35
    ARB
    -3.32
     callback
    -3.26
     crabs
    -3.22
    artz
    -3.18
     HF
    -3.14
    POSITIVE LOGITS
    United
    6.17
     Trafford
    6.13
    united
    5.57
    Manchester
    5.39
     Manchester
    5.37
     United
    5.33
     UNITED
    5.26
     Ferdinand
    4.32
     Fernand
    4.29
     Ferguson
    4.23
    Activations Density 0.017%

    No Known Activations