© 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. 5-ATT-KK
    11. 28355
    Prev
    Next
    INDEX
    Explanations

    concepts related to science, its advancement, and the conflict between scientific evidence and skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.06
    3:0.06
    4:0.04
    5:0.05
    6:0.04
    7:0.06
    8:0.04
    9:0.05
    10:0.36
    11:0.16
    Negative Logits
     Kush
    -1.45
    ydia
    -1.43
     Gamb
    -1.42
     smokes
    -1.41
    ayne
    -1.39
     Maver
    -1.29
    Lago
    -1.28
    ulla
    -1.24
    chini
    -1.24
     FY
    -1.23
    POSITIVE LOGITS
    Science
    1.68
    icist
    1.60
    scientific
    1.54
    Fact
    1.41
    science
    1.41
    ��
    1.40
     scientists
    1.39
    gorithm
    1.39
     physicists
    1.38
     truths
    1.35
    Activations Density 0.165%

    No Known Activations