© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 2916
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "man" and references to Congressman Barton

    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
    0:0.10
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.27
    7:0.04
    8:0.07
    9:0.18
    10:0.02
    11:0.05
    Negative Logits
     Hyundai
    -3.88
    inyl
    -3.86
    undai
    -3.51
     shif
    -3.45
    nih
    -3.30
     NEC
    -3.23
    sequence
    -3.22
    ince
    -3.22
    chwitz
    -3.22
    lig
    -3.19
    POSITIVE LOGITS
     Barton
    11.36
    arton
    5.59
     Bridges
    4.90
     Boulder
    4.33
     Barr
    4.31
     Sutherland
    4.30
     Beacon
    4.27
     Cannon
    4.18
     Bard
    4.15
     Aero
    4.14
    Activations Density 0.000%

    No Known Activations