© 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. 10-ATT-KK
    11. 14506
    Prev
    Next
    INDEX
    Explanations

    punctuation and structures indicating facts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.08
    2:0.10
    3:0.05
    4:0.04
    5:0.03
    6:0.08
    7:0.12
    8:0.03
    9:0.07
    10:0.16
    11:0.03
    Negative Logits
    York
    -2.84
     Cary
    -2.73
     ath
    -2.65
     ADA
    -2.54
     Barron
    -2.49
    iary
    -2.45
     dragon
    -2.45
     Scal
    -2.45
    TON
    -2.44
     mages
    -2.42
    POSITIVE LOGITS
     Luk
    8.60
     Buk
    4.08
     Belarus
    3.99
     Lub
    3.58
     Kos
    3.54
    Uk
    3.53
     Dmit
    3.43
     Donetsk
    3.42
     Kor
    3.35
     Kik
    3.33
    Activations Density 0.001%

    No Known Activations