© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 23871
    Prev
    Next
    INDEX
    Explanations

    demographic statistics and the political affiliations of Americans, particularly focusing on differences between age groups and independent voters

    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
    1:0.09
    2:0.08
    3:0.10
    4:0.16
    5:0.09
    6:0.05
    7:0.06
    8:0.04
    9:0.06
    10:0.11
    11:0.05
    Negative Logits
     bc
    -2.52
     000000
    -2.46
    Register
    -2.28
     QUEST
    -2.25
     Gabriel
    -2.24
     HY
    -2.21
     Etsy
    -2.19
     Kah
    -2.18
    arthed
    -2.17
    CBC
    -2.10
    POSITIVE LOGITS
    utral
    2.77
     views
    2.48
    ages
    2.47
     divides
    2.36
     accompanies
    2.35
     extends
    2.30
    among
    2.30
     strokes
    2.27
     stands
    2.26
     compares
    2.21
    Activations Density 0.006%

    No Known Activations