Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14690
    Prev
    Next
    INDEX
    Explanations

    references to or discussions about ambiguity and uncertainty

    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
    1:0.05
    2:0.38
    3:0.04
    4:0.06
    5:0.14
    6:0.02
    7:0.07
    8:0.06
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
    �醒
    -3.43
    EStream
    -3.33
    ciating
    -3.19
    �
    -2.94
    Repl
    -2.90
    ソ
    -2.86
    hess
    -2.81
    vs
    -2.76
    �
    -2.75
    フォ
    -2.74
    POSITIVE LOGITS
     may
    6.56
     MAY
    5.00
    may
    4.75
     May
    3.53
    May
    3.21
     might
    3.15
     shall
    3.08
     appears
    2.67
     mileage
    2.66
    yip
    2.65
    Activations Density 0.061%

    No Known Activations