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. 9-ATT-KK
    6. 7654
    Prev
    Next
    INDEX
    Explanations

    specific phrases indicating data points in a discussion about system performance or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.12
    1:0.03
    2:0.09
    3:0.05
    4:0.04
    5:0.05
    6:0.21
    7:0.05
    8:0.05
    9:0.16
    10:0.04
    11:0.04
    Negative Logits
     Yates
    -3.94
     Clarke
    -3.86
     Abortion
    -3.62
     Wilson
    -3.60
    Clar
    -3.53
     Bayer
    -3.52
     Cunningham
    -3.47
    paren
    -3.42
     CIS
    -3.41
     Broadcast
    -3.40
    POSITIVE LOGITS
     loot
    8.36
     Loot
    7.44
     looting
    7.37
     treasure
    7.12
     Treasure
    6.54
     treasures
    5.90
     looted
    5.82
     plunder
    5.59
     hoard
    5.25
     scaven
    5.08
    Activations Density 0.000%

    No Known Activations