© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20125
    Prev
    Next
    INDEX
    Explanations

    sentences that express criticism or condemnation of political actions and statements

    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
    0:0.06
    1:0.01
    2:0.06
    3:0.03
    4:0.07
    5:0.03
    6:0.23
    7:0.06
    8:0.08
    9:0.24
    10:0.02
    11:0.04
    Negative Logits
     pengu
    -4.36
     hurricanes
    -3.68
     Jupiter
    -3.59
     spons
    -3.45
    oz
    -3.43
     Coco
    -3.43
     Coc
    -3.34
     gol
    -3.31
     Antarctica
    -3.31
    ogly
    -3.30
    POSITIVE LOGITS
     Reid
    11.56
     Reeves
    5.87
     Reed
    4.96
     Schumer
    4.87
     McConnell
    4.64
     Bundy
    4.43
     Reynolds
    4.39
     Payne
    4.33
     Levin
    4.33
     Neh
    4.15
    Activations Density 0.005%

    No Known Activations