© 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. 12307
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or incidents in a narrative context

    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
    0:0.05
    1:0.01
    2:0.06
    3:0.08
    4:0.03
    5:0.05
    6:0.03
    7:0.06
    8:0.50
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
     Milwaukee
    -4.15
     Arkham
    -3.74
     Bucks
    -3.60
    aukee
    -3.49
     Manit
    -3.35
    Mil
    -3.34
    Wisconsin
    -3.21
     Berks
    -3.18
     Pittsburgh
    -3.17
    Madison
    -3.13
    POSITIVE LOGITS
     Taiwanese
    7.47
     Nguyen
    7.37
     Vietnamese
    7.23
    Hong
    6.82
     Ng
    6.74
     Cambod
    6.55
     Thai
    6.52
     Huang
    6.48
    Tai
    6.45
     Malays
    6.44
    Activations Density 0.493%

    No Known Activations