© 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. 13272
    Prev
    Next
    INDEX
    Explanations

    statements that involve logical reasoning or commentary on human behavior

    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
    0:0.22
    1:0.11
    2:0.08
    3:0.04
    4:0.04
    5:0.04
    6:0.10
    7:0.09
    8:0.02
    9:0.06
    10:0.12
    11:0.03
    Negative Logits
     Nex
    -3.75
     Bild
    -3.37
    Iraq
    -3.27
     Afgh
    -3.24
     poppy
    -3.22
     haz
    -3.21
     Dot
    -3.20
    Mos
    -3.17
    rupal
    -3.03
     destruct
    -3.02
    POSITIVE LOGITS
     Stevenson
    9.79
    Steven
    5.07
     Stevens
    4.70
     Swanson
    4.11
     Livingston
    3.68
     Steven
    3.54
     Humph
    3.50
     Eaton
    3.47
     Sturgeon
    3.40
     Stein
    3.37
    Activations Density 0.001%

    No Known Activations