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. 10-ATT-KK
    6. 14681
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names associated with legal cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.07
    2:0.06
    3:0.07
    4:0.06
    5:0.04
    6:0.08
    7:0.10
    8:0.03
    9:0.06
    10:0.15
    11:0.08
    Negative Logits
     Rudy
    -3.33
     Cisco
    -3.06
     Mirage
    -2.91
     Natasha
    -2.82
     Ghostbusters
    -2.81
     Omni
    -2.77
     UD
    -2.75
     Barkley
    -2.66
     Deadpool
    -2.63
     dispatcher
    -2.62
    POSITIVE LOGITS
     wh
    4.27
     whale
    3.44
     whales
    3.32
     Whale
    3.29
     Antarctic
    3.23
     サ
    3.17
     �
    3.13
    Japan
    3.00
     Fisheries
    2.98
     �
    2.93
    Activations Density 0.000%

    No Known Activations