© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14985
    Prev
    Next
    INDEX
    Explanations

    mentions of judicial rulings or decisions made by the Supreme Court

    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
    0:0.43
    1:0.02
    2:0.09
    3:0.10
    4:0.05
    5:0.04
    6:0.02
    7:0.05
    8:0.04
    9:0.03
    10:0.06
    11:0.02
    Negative Logits
     distributors
    -2.36
     distributor
    -2.31
     Sell
    -2.31
     seller
    -2.31
     suppliers
    -2.17
    Canadian
    -2.14
     exhib
    -2.13
     organizers
    -2.12
     Marketplace
    -2.11
     purchaser
    -2.08
    POSITIVE LOGITS
     vacancy
    2.59
     Recording
    2.42
     selfie
    2.39
     TAMADRA
    2.36
     Xperia
    2.34
     Ezra
    2.30
     Jelly
    2.25
     vacancies
    2.24
     Speech
    2.14
     Chromebook
    2.10
    Activations Density 0.029%

    No Known Activations