© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6635
    Prev
    Next
    INDEX
    Explanations

    instances of negotiation and trade-related language

    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
    0:0.11
    1:0.03
    2:0.07
    3:0.04
    4:0.06
    5:0.05
    6:0.22
    7:0.04
    8:0.12
    9:0.12
    10:0.04
    11:0.05
    Negative Logits
    worms
    -4.02
     Rosenberg
    -3.84
     Armory
    -3.84
     uranium
    -3.82
    worm
    -3.73
    >>
    -3.69
     Braun
    -3.67
    Jews
    -3.66
    oths
    -3.65
     Goldberg
    -3.65
    POSITIVE LOGITS
     Cout
    10.75
     Cot
    5.52
     Fernand
    4.76
     cout
    4.75
     Philippe
    4.62
     Dele
    4.41
     Bout
    4.26
     Coco
    3.97
     Brendan
    3.88
     Cors
    3.84
    Activations Density 0.001%

    No Known Activations