© 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. 20812
    Prev
    Next
    INDEX
    Explanations

    references to government officials and ministers along with their actions or 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
    0:0.07
    1:0.02
    2:0.09
    3:0.10
    4:0.03
    5:0.09
    6:0.03
    7:0.07
    8:0.36
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
     Pittsburgh
    -3.35
     Lyft
    -3.33
     Brooklyn
    -3.26
    Atlanta
    -3.24
     Philly
    -3.20
     Cleveland
    -3.17
     Albuquerque
    -3.15
    sburgh
    -3.15
     Frazier
    -3.11
    querque
    -3.08
    POSITIVE LOGITS
     Canberra
    6.43
     Parliament
    6.36
     Parliamentary
    6.13
    Australia
    5.80
     parliament
    5.78
     parliamentary
    5.62
     ministerial
    5.59
     MPs
    5.58
     Ministers
    5.53
     Minister
    5.29
    Activations Density 0.408%

    No Known Activations