© 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. 21839
    Prev
    Next
    INDEX
    Explanations

    terminology related to grading and evaluations

    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
    0:0.13
    1:0.03
    2:0.07
    3:0.06
    4:0.03
    5:0.04
    6:0.28
    7:0.02
    8:0.03
    9:0.18
    10:0.02
    11:0.04
    Negative Logits
    セ
    -3.75
    heter
    -3.61
     Nightmares
    -3.46
     hut
    -3.38
     Hemp
    -3.29
     Homeless
    -3.25
     teleportation
    -3.18
     Kau
    -3.17
     wom
    -3.15
     cafe
    -3.11
    POSITIVE LOGITS
     Grade
    8.73
    Grade
    7.90
     grade
    7.80
     grades
    7.56
     grading
    7.05
    grade
    6.26
    grades
    6.17
     graded
    6.03
     GPA
    5.36
    graded
    5.13
    Activations Density 0.002%

    No Known Activations