© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17194
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss legal implications or judicial processes

    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
    0:0.07
    1:0.03
    2:0.08
    3:0.03
    4:0.06
    5:0.02
    6:0.25
    7:0.04
    8:0.06
    9:0.25
    10:0.02
    11:0.03
    Negative Logits
    ataka
    -4.28
     char
    -4.19
     Cind
    -3.82
     carn
    -3.73
    Char
    -3.73
    acho
    -3.63
    char
    -3.48
     cel
    -3.45
     tempt
    -3.43
    ashtra
    -3.40
    POSITIVE LOGITS
     Zimmerman
    11.12
     Zimmer
    8.65
     Trayvon
    6.01
     Frazier
    4.75
    azer
    4.32
     Jury
    4.13
    imer
    4.12
     Neander
    4.10
    zer
    4.08
     Berman
    4.06
    Activations Density 0.002%

    No Known Activations