© 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. 573
    Prev
    Next
    INDEX
    Explanations

    references to processes or conditions that indicate a need for clarification or correction in factual statements

    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
    0:0.15
    1:0.03
    2:0.06
    3:0.04
    4:0.03
    5:0.03
    6:0.24
    7:0.03
    8:0.06
    9:0.24
    10:0.03
    11:0.03
    Negative Logits
     Marqu
    -3.90
    athe
    -3.77
     Patty
    -3.75
     marqu
    -3.53
     Brewers
    -3.52
    tta
    -3.52
     Laur
    -3.32
     Hath
    -3.31
    ngth
    -3.29
     Eck
    -3.29
    POSITIVE LOGITS
     Sim
    10.23
    Sim
    10.08
     sim
    8.56
    sim
    7.81
     Sims
    7.68
     Simulation
    7.52
     simulator
    7.42
    SIM
    7.24
     simulation
    7.17
     SIM
    7.02
    Activations Density 0.008%

    No Known Activations