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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14853
    Prev
    Next
    INDEX
    Explanations

    instances of quotations or indicative punctuation that might reveal spoken statements or claims

    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
    1:0.09
    2:0.08
    3:0.08
    4:0.05
    5:0.02
    6:0.06
    7:0.12
    8:0.04
    9:0.04
    10:0.13
    11:0.09
    Negative Logits
     Bard
    -3.42
    DCS
    -3.23
    ornia
    -3.04
     KD
    -2.91
     Royals
    -2.89
     RC
    -2.89
     Cavs
    -2.74
     Turtles
    -2.74
     Rolls
    -2.73
     Clarkson
    -2.64
    POSITIVE LOGITS
     Homo
    5.23
     Neander
    4.82
     Africans
    3.54
    anthrop
    3.48
    African
    3.21
     Anthropology
    3.15
     Hut
    3.12
     Anthrop
    3.03
     chimpanzees
    3.02
     Austral
    2.99
    Activations Density 0.001%

    No Known Activations