© 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. 12255
    Prev
    Next
    INDEX
    Explanations

    specific names and titles related to government officials and organizations

    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
    1:0.02
    2:0.06
    3:0.08
    4:0.03
    5:0.06
    6:0.05
    7:0.04
    8:0.42
    9:0.04
    10:0.02
    11:0.04
    Negative Logits
    Wisconsin
    -5.40
     Pittsburgh
    -5.14
     Milwaukee
    -5.08
     Wisconsin
    -4.95
     Erie
    -4.48
    Ohio
    -4.41
    Pitt
    -4.40
     Vermont
    -4.30
    Michigan
    -4.18
     Madison
    -4.16
    POSITIVE LOGITS
     Malays
    9.08
     Malaysian
    8.67
     Malaysia
    8.60
     Kuala
    8.17
     Lumpur
    6.72
     Indonesian
    5.75
     Indones
    5.65
    Mal
    5.60
     Brune
    5.49
     Singapore
    5.49
    Activations Density 0.059%

    No Known Activations