© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15435
    Prev
    Next
    INDEX
    Explanations

    indicators of uncertainty and measurement of performance in card games

    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
    1:0.11
    2:0.05
    3:0.06
    4:0.21
    5:0.02
    6:0.08
    7:0.12
    8:0.02
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
    luaj
    -2.44
    ynthesis
    -2.35
     Shade
    -2.30
    flush
    -2.21
    bucks
    -2.20
    ilar
    -2.18
     takedown
    -2.17
    venge
    -2.17
    ��
    -2.13
    atche
    -2.13
    POSITIVE LOGITS
     uncertainty
    6.16
     uncertainties
    5.41
     uncertain
    4.80
     certainty
    4.06
     ambiguity
    3.73
     unpredict
    3.62
     Unc
    3.35
     unsure
    3.31
     predict
    3.30
     variability
    3.26
    Activations Density 0.015%

    No Known Activations