© 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. 19769
    Prev
    Next
    INDEX
    Explanations

    references to specific places, actions, and notable counts related to political and social contexts

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.06
    4:0.04
    5:0.05
    6:0.33
    7:0.03
    8:0.09
    9:0.17
    10:0.02
    11:0.05
    Negative Logits
     Tant
    -4.02
     Petra
    -3.90
    PET
    -3.75
     PET
    -3.66
     Punk
    -3.60
     Alexand
    -3.41
    STEM
    -3.40
     sneakers
    -3.38
     Hermes
    -3.37
    Pet
    -3.31
    POSITIVE LOGITS
     county
    8.56
     counties
    8.02
     County
    7.49
     COUNTY
    5.26
     sheriff
    5.17
     Sheriff
    4.40
     rural
    4.25
     parish
    4.14
    Count
    4.07
     Parish
    4.06
    Activations Density 0.028%

    No Known Activations