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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 13778
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or addressing societal issues, policies, and controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.04
    3:0.05
    4:0.35
    5:0.04
    6:0.03
    7:0.02
    8:0.25
    9:0.05
    10:0.04
    11:0.02
    Negative Logits
    ️
    -1.78
    acher
    -1.42
    cius
    -1.41
    TB
    -1.40
     Beetle
    -1.38
    kie
    -1.31
     Chero
    -1.29
     Wen
    -1.28
    lander
    -1.27
    eks
    -1.27
    POSITIVE LOGITS
     sust
    1.83
    ateral
    1.56
    utical
    1.54
    utics
    1.52
     bearer
    1.48
    ersive
    1.42
     resid
    1.40
    andestine
    1.33
    adra
    1.33
     sanctuary
    1.31
    Activations Density 0.017%

    No Known Activations