© 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. 14266
    Prev
    Next
    INDEX
    Explanations

    mention of legal proceedings and their ramifications

    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
    1:0.02
    2:0.06
    3:0.03
    4:0.04
    5:0.03
    6:0.29
    7:0.04
    8:0.08
    9:0.23
    10:0.03
    11:0.02
    Negative Logits
     sarc
    -3.88
     Carth
    -3.65
    Saharan
    -3.57
     Livingston
    -3.56
    Jac
    -3.48
    isine
    -3.48
     Monaco
    -3.46
     Africans
    -3.44
    Lewis
    -3.39
    Force
    -3.30
    POSITIVE LOGITS
     Bud
    11.30
     bud
    7.58
     buds
    6.15
     Buddy
    5.94
     Budd
    5.82
     Bun
    5.27
     Rud
    4.59
     Bayer
    4.59
     Byr
    4.53
     bun
    4.44
    Activations Density 0.002%

    No Known Activations