© 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. 10-ATT-KK
    11. 13712
    Prev
    Next
    INDEX
    Explanations

    elements relating to political actions and public opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.23
    1:0.03
    2:0.05
    3:0.08
    4:0.03
    5:0.02
    6:0.11
    7:0.12
    8:0.01
    9:0.03
    10:0.21
    11:0.02
    Negative Logits
     Rabbit
    -3.74
    Í
    -3.63
     Trinidad
    -3.46
     Bunny
    -3.45
     Sultan
    -3.35
     NRL
    -3.34
     Danish
    -3.31
     Ecuador
    -3.28
     Fiji
    -3.26
    Turkish
    -3.22
    POSITIVE LOGITS
     Michigan
    7.84
    Michigan
    7.79
     Wolver
    7.28
     Mich
    6.87
     Lansing
    6.86
    Mich
    5.89
     Flint
    5.54
     MI
    5.52
     Detroit
    5.42
     Spartans
    5.33
    Activations Density 0.047%

    No Known Activations