© 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. 20251
    Prev
    Next
    INDEX
    Explanations

    references to actions or events that involve change or exchange

    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
    0:0.05
    1:0.04
    2:0.07
    3:0.05
    4:0.03
    5:0.02
    6:0.05
    7:0.11
    8:0.02
    9:0.03
    10:0.45
    11:0.03
    Negative Logits
     Mel
    -3.29
     Lil
    -3.12
     Vest
    -2.90
     Lima
    -2.81
     Thr
    -2.76
     Por
    -2.70
     Hats
    -2.68
     Vanderbilt
    -2.65
    hap
    -2.65
    innon
    -2.61
    POSITIVE LOGITS
     Q
    10.56
    Q
    9.19
     q
    7.53
    q
    6.70
     Qt
    6.58
    qt
    6.43
    QL
    5.88
     QR
    5.86
     Qu
    5.29
    qs
    5.24
    Activations Density 0.110%

    No Known Activations