© 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. 16811
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proposals or adjustments, particularly related to a group or consensus

    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
    0:0.11
    1:0.15
    2:0.05
    3:0.04
    4:0.03
    5:0.02
    6:0.21
    7:0.09
    8:0.02
    9:0.03
    10:0.15
    11:0.04
    Negative Logits
     Beir
    -3.19
     Rag
    -3.00
    arag
    -2.93
    LG
    -2.92
     GOT
    -2.65
     lit
    -2.60
    farm
    -2.58
     Rut
    -2.57
    BG
    -2.55
     Rik
    -2.45
    POSITIVE LOGITS
     Conc
    8.96
     conc
    7.68
     CONC
    4.23
     Con
    4.05
     concussion
    3.69
    con
    3.65
     concurrent
    3.60
    Con
    3.48
     CONS
    3.29
     Cons
    3.23
    Activations Density 0.001%

    No Known Activations