© 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. 10891
    Prev
    Next
    INDEX
    Explanations

    references to questions and responses within the text

    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
    0:0.09
    1:0.06
    2:0.06
    3:0.05
    4:0.06
    5:0.05
    6:0.14
    7:0.05
    8:0.08
    9:0.25
    10:0.02
    11:0.05
    Negative Logits
     Pelosi
    -4.34
     Purdue
    -3.64
    WP
    -3.55
     Boe
    -3.49
     Anaheim
    -3.35
     Buffalo
    -3.35
     Dive
    -3.28
     Fresno
    -3.27
     Spokane
    -3.27
    azine
    -3.24
    POSITIVE LOGITS
    Sir
    8.91
     Sir
    8.44
     Sirius
    5.23
     Sev
    4.11
     sir
    4.06
    IR
    3.83
    Scotland
    3.59
     Strat
    3.52
    STON
    3.52
     Stewart
    3.51
    Activations Density 0.003%

    No Known Activations