© 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. 14460
    Prev
    Next
    INDEX
    Explanations

    contextual cues related to uncertainty and conflicting information

    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
    0:0.17
    1:0.10
    2:0.06
    3:0.03
    4:0.03
    5:0.02
    6:0.07
    7:0.15
    8:0.03
    9:0.03
    10:0.21
    11:0.04
    Negative Logits
    agher
    -2.81
    ixel
    -2.68
     Zimmer
    -2.67
     Gard
    -2.65
    iste
    -2.62
    ️
    -2.60
    Frameworks
    -2.58
     glide
    -2.53
    assetsadobe
    -2.53
    ZX
    -2.51
    POSITIVE LOGITS
     Pul
    9.00
     pul
    6.52
     Sul
    4.70
     pulp
    4.54
     Kul
    4.25
     Ul
    3.99
     Patt
    3.52
     Lump
    3.43
     Ful
    3.29
    Ul
    3.21
    Activations Density 0.002%

    No Known Activations