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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2929
    Prev
    Next
    INDEX
    Explanations

    mentions of lawsuits and legal actions

    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
    1:0.05
    2:0.06
    3:0.03
    4:0.03
    5:0.03
    6:0.24
    7:0.03
    8:0.04
    9:0.23
    10:0.02
    11:0.06
    Negative Logits
     Hass
    -4.58
    hom
    -4.04
    gdala
    -3.88
     Leban
    -3.86
     Christensen
    -3.85
     TAM
    -3.81
     Hendricks
    -3.68
    amus
    -3.66
     Tasman
    -3.56
     Jem
    -3.56
    POSITIVE LOGITS
    Roll
    8.78
    rolling
    7.34
     roll
    7.31
     Roll
    7.30
    roll
    6.88
    rolled
    6.74
     Rolling
    6.43
     rolling
    6.39
     rolls
    6.34
     Rolls
    6.28
    Activations Density 0.003%

    No Known Activations