© 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. 19756
    Prev
    Next
    INDEX
    Explanations

    key technical terms and functionality related to software definitions and configurations

    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
    0:0.16
    1:0.12
    2:0.09
    3:0.04
    4:0.03
    5:0.03
    6:0.10
    7:0.12
    8:0.03
    9:0.03
    10:0.17
    11:0.04
    Negative Logits
     Randolph
    -3.13
     Kad
    -3.11
     lizard
    -3.02
     Ald
    -2.95
    arag
    -2.82
     Eag
    -2.82
     Pav
    -2.82
     Ramp
    -2.79
     Quin
    -2.69
     Sorce
    -2.66
    POSITIVE LOGITS
    BS
    6.35
     BS
    6.20
    BN
    4.10
     Blitz
    3.60
     MS
    3.57
    bps
    3.24
     Brees
    3.23
    bs
    3.17
    bt
    3.16
     Bis
    3.14
    Activations Density 0.001%

    No Known Activations