© 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. 23306
    Prev
    Next
    INDEX
    Explanations

    expressions indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.05
    1:0.05
    2:0.02
    3:0.04
    4:0.05
    5:0.10
    6:0.04
    7:0.03
    8:0.04
    9:0.40
    10:0.04
    11:0.08
    Negative Logits
     tracts
    -2.24
    romy
    -2.13
     undertake
    -2.09
     Held
    -2.06
     elders
    -2.02
     recover
    -1.95
     jointly
    -1.92
    ustomed
    -1.92
    orously
    -1.91
     juveniles
    -1.90
    POSITIVE LOGITS
     means
    2.85
     includes
    2.84
     translates
    2.80
     happens
    2.66
     isn
    2.65
    =""
    2.56
    imation
    2.55
     implies
    2.54
     seems
    2.47
     corresponds
    2.44
    Activations Density 0.160%

    No Known Activations