© 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. 10-ATT-KK
    11. 22278
    Prev
    Next
    INDEX
    Explanations

    key phrases and conjunctions related to negotiations and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.02
    3:0.12
    4:0.08
    5:0.02
    6:0.04
    7:0.40
    8:0.01
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Mayweather
    -2.78
     Gon
    -2.52
     Courtney
    -2.44
     Faul
    -2.40
     PLA
    -2.32
     Monica
    -2.29
    Miami
    -2.29
     Maya
    -2.28
     Coleman
    -2.26
     Fiorina
    -2.25
    POSITIVE LOGITS
     tuberculosis
    2.28
     Radical
    2.16
    radical
    2.13
     Bav
    2.13
    ernels
    2.10
     mitochond
    2.10
    odor
    2.07
     lash
    2.06
    rad
    2.06
    erd
    2.04
    Activations Density 0.087%

    No Known Activations