© 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. 7467
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or uncertainty about various topics

    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
    0:0.07
    1:0.02
    2:0.42
    3:0.08
    4:0.10
    5:0.05
    6:0.02
    7:0.03
    8:0.05
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     Newark
    -4.05
     Skydragon
    -3.58
     Wells
    -3.57
     Chavez
    -3.49
     maple
    -3.34
     Wally
    -3.33
     Compass
    -3.31
     Wichita
    -3.24
     Hendricks
    -3.12
     yeast
    -3.07
    POSITIVE LOGITS
    �
    7.39
     �
    6.14
     │
    5.99
    �
    5.46
    �
    5.37
     �
    5.28
    �
    5.22
    �
    5.21
    �
    5.21
     �
    5.14
    Activations Density 1.668%

    No Known Activations