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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18698
    Prev
    Next
    INDEX
    Explanations

    references to specific baseball teams or players

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.05
    4:0.03
    5:0.05
    6:0.07
    7:0.05
    8:0.42
    9:0.06
    10:0.03
    11:0.02
    Negative Logits
     Libyan
    -4.23
     Halifax
    -4.16
    Michigan
    -4.07
     Scotia
    -4.00
     Wolver
    -3.96
     Libya
    -3.72
    Saudi
    -3.67
     Afghans
    -3.62
     Tripoli
    -3.57
     Kabul
    -3.52
    POSITIVE LOGITS
     Kers
    7.46
     Dodgers
    7.15
     Dod
    5.12
    Los
    4.69
     Yas
    4.50
     NL
    4.50
     Tsu
    4.48
     Pu
    4.33
     Hiro
    4.08
     Choi
    4.01
    Activations Density 0.014%

    No Known Activations