© 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. 9088
    Prev
    Next
    INDEX
    Explanations

    instances of communication and expression in political contexts

    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
    0:0.13
    1:0.14
    2:0.08
    3:0.03
    4:0.03
    5:0.02
    6:0.07
    7:0.10
    8:0.02
    9:0.03
    10:0.27
    11:0.04
    Negative Logits
    amon
    -3.21
     proc
    -2.97
     mon
    -2.93
    gdala
    -2.86
     Bihar
    -2.79
     monkeys
    -2.78
     Jindal
    -2.71
     Afric
    -2.69
    phony
    -2.68
    atel
    -2.68
    POSITIVE LOGITS
     Ste
    9.80
    Ste
    8.07
    ste
    6.68
     ste
    6.59
     STE
    6.50
    STE
    5.47
     Stein
    4.47
     Stella
    4.38
     steak
    4.13
     Schwe
    3.97
    Activations Density 0.021%

    No Known Activations