© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15158
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate observations or reports

    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
    1:0.09
    2:0.07
    3:0.06
    4:0.05
    5:0.04
    6:0.11
    7:0.10
    8:0.04
    9:0.06
    10:0.11
    11:0.05
    Negative Logits
     Cherokee
    -3.39
     Throne
    -3.17
     Chero
    -3.10
    Utah
    -2.96
     synagogue
    -2.83
     Trey
    -2.80
     Antar
    -2.75
    Scot
    -2.75
    ority
    -2.73
     Trib
    -2.71
    POSITIVE LOGITS
     Marcel
    7.08
     Blanc
    3.73
     Brazilian
    3.56
     Klaus
    3.43
     Paragu
    3.37
     Urug
    3.29
     Spr
    3.23
    Brazil
    3.23
     spr
    3.20
    cel
    3.18
    Activations Density 0.000%

    No Known Activations