© 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 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. 21934
    Prev
    Next
    INDEX
    Explanations

    references to challenges and controversies faced, particularly in political 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
    0:0.34
    1:0.01
    2:0.24
    3:0.07
    4:0.02
    5:0.04
    6:0.02
    7:0.03
    8:0.03
    9:0.02
    10:0.12
    11:0.02
    Negative Logits
     deleted
    -3.03
     warranties
    -2.72
     transmissions
    -2.64
     Warranty
    -2.63
     warranty
    -2.62
     backups
    -2.60
     Clip
    -2.59
     transmission
    -2.58
     STD
    -2.54
     liner
    -2.51
    POSITIVE LOGITS
     challenge
    3.64
    Chall
    3.44
     Challenges
    3.38
     challenges
    3.31
    chall
    3.29
     Challenge
    3.27
     challenging
    3.02
     Chall
    2.97
    Beg
    2.91
     daunting
    2.83
    Activations Density 0.011%

    No Known Activations