© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12226
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or negation

    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
    0:0.02
    1:0.04
    2:0.04
    3:0.06
    4:0.06
    5:0.05
    6:0.02
    7:0.06
    8:0.47
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    kefeller
    -3.40
     namely
    -3.26
    arthed
    -2.41
     viz
    -2.28
    conservancy
    -2.26
    ilitarian
    -2.07
     Vaugh
    -2.06
    \":
    -2.06
    channelAvailability
    -1.99
    sbm
    -1.98
    POSITIVE LOGITS
    ,
    6.53
    ,...
    5.21
    ,,
    4.36
    ?,
    4.10
    !,
    4.10
    .,
    4.08
    ,[
    3.84
    ,.
    3.73
    ,-
    3.70
    *,
    3.67
    Activations Density 0.537%

    No Known Activations