© 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. 1106
    Prev
    Next
    INDEX
    Explanations

    references to political processes and discussions

    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
    0:0.09
    1:0.02
    2:0.06
    3:0.03
    4:0.07
    5:0.04
    6:0.23
    7:0.08
    8:0.08
    9:0.19
    10:0.02
    11:0.04
    Negative Logits
     mog
    -3.74
    ramid
    -3.71
    vg
    -3.67
     sandwiches
    -3.65
     Franch
    -3.60
    pack
    -3.60
     fortun
    -3.48
     Palest
    -3.37
     mixer
    -3.36
    Vill
    -3.34
    POSITIVE LOGITS
     Clarke
    11.97
    Clar
    9.59
     Calder
    5.93
     Lawson
    4.72
     Brennan
    4.71
     Clark
    4.67
     Clar
    4.60
    Ba
    4.56
     Lex
    4.51
     Bailey
    4.46
    Activations Density 0.005%

    No Known Activations