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. 3-ATT-KK
    6. 8606
    Prev
    Next
    INDEX
    Explanations

    the presence of 'watch faces' and related features in applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.04
    2:0.07
    3:0.10
    4:0.10
    5:0.05
    6:0.07
    7:0.12
    8:0.06
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
    enza
    -1.18
    iliary
    -1.03
    ADVERTISEMENT
    -1.02
    ogun
    -1.01
    neau
    -0.99
     voc
    -0.99
    urat
    -0.95
    ‎
    -0.94
    taboola
    -0.93
    kell
    -0.93
    POSITIVE LOGITS
    ETH
    1.12
    し
    1.07
    CHA
    1.05
    の�
    1.02
    ANY
    1.00
     NON
    0.99
    FIN
    0.99
     Maiden
    0.99
    eers
    0.96
     halves
    0.95
    Activations Density 0.047%

    No Known Activations