© 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. 9715
    Prev
    Next
    INDEX
    Explanations

    references to requirements and constraints in a context involving requests or needs

    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
    0:0.15
    1:0.18
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.05
    7:0.09
    8:0.02
    9:0.05
    10:0.16
    11:0.05
    Negative Logits
     nud
    -3.10
     Nad
    -2.78
     CLS
    -2.72
     snug
    -2.68
    ł
    -2.67
    rug
    -2.61
    ussen
    -2.58
     Rut
    -2.58
     Uncharted
    -2.56
     Matthews
    -2.53
    POSITIVE LOGITS
     Flame
    8.68
     flame
    6.79
    flame
    5.85
     Flam
    5.57
     Flames
    4.83
     flames
    4.38
     Flare
    4.12
    Fl
    3.99
     Fl
    3.94
     burner
    3.90
    Activations Density 0.001%

    No Known Activations