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. 7644
    Prev
    Next
    INDEX
    Explanations

    references to sports events and matchups

    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
    0:0.19
    1:0.03
    2:0.06
    3:0.14
    4:0.11
    5:0.11
    6:0.03
    7:0.10
    8:0.04
    9:0.02
    10:0.08
    11:0.05
    Negative Logits
     cannabin
    -1.99
     constit
    -1.97
     handwriting
    -1.95
     counterfe
    -1.94
     affidav
    -1.91
     poems
    -1.85
     prolifer
    -1.85
    adra
    -1.84
     disadvant
    -1.83
    �
    -1.81
    POSITIVE LOGITS
     ESPN
    3.08
     airs
    2.80
    ESPN
    2.76
     SPORTS
    2.71
    CAST
    2.62
     airing
    2.58
     TBA
    2.53
    cast
    2.48
     Show
    2.47
    Coach
    2.44
    Activations Density 0.126%

    No Known Activations