© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21646
    Prev
    Next
    INDEX
    Explanations

    statements involving legal conclusions or opinions

    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
    0:0.11
    1:0.03
    2:0.13
    3:0.04
    4:0.03
    5:0.04
    6:0.21
    7:0.03
    8:0.08
    9:0.19
    10:0.02
    11:0.03
    Negative Logits
     Slime
    -3.53
    ugu
    -3.46
     Boris
    -3.42
    Fish
    -3.35
     Fork
    -3.34
     Yug
    -3.33
    ooks
    -3.33
     fishing
    -3.30
    sle
    -3.29
     Rw
    -3.23
    POSITIVE LOGITS
     Anthem
    11.24
     anthem
    6.81
     AVG
    5.16
     patriotism
    4.39
     Herrera
    4.34
    eta
    4.13
     Kaepernick
    4.06
     Manz
    4.06
    Ant
    3.95
     IPA
    3.94
    Activations Density 0.001%

    No Known Activations