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. 13786
    Prev
    Next
    INDEX
    Explanations

    references to homemade food and drinks or DIY-related terms

    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
    0:0.05
    1:0.05
    2:0.16
    3:0.11
    4:0.11
    5:0.09
    6:0.02
    7:0.03
    8:0.09
    9:0.17
    10:0.05
    11:0.03
    Negative Logits
    hematically
    -1.59
    xus
    -1.44
    forth
    -1.38
     Statistical
    -1.33
    antically
    -1.26
    HUD
    -1.26
     Watson
    -1.26
    ��
    -1.24
     Tillerson
    -1.23
    ":"/
    -1.21
    POSITIVE LOGITS
     hobby
    1.46
     accompan
    1.39
     kits
    1.36
     chore
    1.31
    Bul
    1.29
     decoration
    1.29
     arrang
    1.26
     carts
    1.22
     guide
    1.22
     Patch
    1.22
    Activations Density 0.009%

    No Known Activations