© 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. 2603
    Prev
    Next
    INDEX
    Explanations

    quotes from players and coaches discussing their performance and perspectives

    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
    1:0.04
    2:0.13
    3:0.17
    4:0.09
    5:0.04
    6:0.01
    7:0.06
    8:0.05
    9:0.01
    10:0.24
    11:0.01
    Negative Logits
     coerc
    -2.37
     FOIA
    -2.31
    successfully
    -2.24
     starve
    -2.24
     contra
    -2.15
     commissions
    -2.15
    igmat
    -2.12
     NGOs
    -2.08
     malaria
    -2.07
     malf
    -2.06
    POSITIVE LOGITS
     coach
    3.40
    Said
    3.35
    Coach
    3.27
     Coach
    3.00
     joked
    2.68
     preseason
    2.63
    UFC
    2.63
    ESPN
    2.59
     locker
    2.57
     quarterback
    2.54
    Activations Density 0.019%

    No Known Activations