© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21143
    Prev
    Next
    INDEX
    Explanations

    references to opinions or statements made by individuals, particularly in formal contexts

    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
    0:0.07
    1:0.39
    2:0.05
    3:0.04
    4:0.03
    5:0.02
    6:0.09
    7:0.08
    8:0.02
    9:0.02
    10:0.10
    11:0.05
    Negative Logits
     lav
    -3.20
    Marginal
    -2.98
    orable
    -2.87
    nces
    -2.71
    Electric
    -2.58
     Peb
    -2.52
    lest
    -2.52
    Kal
    -2.43
    pour
    -2.42
    Dub
    -2.41
    POSITIVE LOGITS
     Cross
    9.24
     cross
    8.82
    Cross
    8.54
    cross
    8.39
     crosses
    6.53
     crossed
    5.54
     crossing
    4.95
     Crossing
    4.94
     crossings
    4.16
     Multi
    3.35
    Activations Density 0.049%

    No Known Activations