© 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. 12308
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research reports

    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
    0:0.02
    1:0.02
    2:0.04
    3:0.05
    4:0.11
    5:0.33
    6:0.03
    7:0.03
    8:0.03
    9:0.25
    10:0.02
    11:0.03
    Negative Logits
     outwe
    -3.87
     stayed
    -3.53
     remained
    -3.31
     lasted
    -3.26
     ceased
    -3.24
     tended
    -3.18
     mattered
    -3.12
     lacked
    -3.08
     proceeded
    -3.01
     depended
    -2.98
    POSITIVE LOGITS
     warns
    4.08
     reveals
    3.93
     proposes
    3.78
     suggests
    3.78
     predicts
    3.54
     examines
    3.42
     threatens
    3.40
     argues
    3.37
    Researchers
    3.21
     Reve
    3.19
    Activations Density 0.070%

    No Known Activations