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. 14616
    Prev
    Next
    INDEX
    Explanations

    phrases related to predictions and expectations in sports contexts

    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
    0:0.21
    1:0.07
    2:0.07
    3:0.07
    4:0.04
    5:0.03
    6:0.13
    7:0.08
    8:0.03
    9:0.05
    10:0.10
    11:0.06
    Negative Logits
     Gamma
    -3.27
     Walsh
    -3.17
     Dartmouth
    -2.96
     Whitman
    -2.88
    pine
    -2.82
     Spiegel
    -2.81
    gon
    -2.80
    プ
    -2.79
    ifax
    -2.75
     behavi
    -2.72
    POSITIVE LOGITS
     Royals
    7.34
    Roy
    4.86
     KC
    4.72
    Kansas
    4.46
     Herrera
    4.44
     Kansas
    4.36
     Kers
    4.18
     Ventura
    3.93
     ERA
    3.81
     Kend
    3.68
    Activations Density 0.002%

    No Known Activations