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. 7-ATT-KK
    6. 18933
    Prev
    Next
    INDEX
    Explanations

    occurrences of waking up and the emotions or thoughts associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.02
    3:0.16
    4:0.06
    5:0.09
    6:0.03
    7:0.03
    8:0.33
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
     merits
    -1.78
    ⓘ
    -1.73
    worthiness
    -1.71
    alties
    -1.66
     Promotion
    -1.65
     promotion
    -1.57
     prizes
    -1.55
     promotions
    -1.53
    Benef
    -1.52
     endorsements
    -1.50
    POSITIVE LOGITS
     sleepy
    2.04
     woke
    2.00
     awake
    1.93
     depressed
    1.91
     refreshed
    1.89
     waking
    1.88
     wake
    1.85
     startled
    1.77
     feeling
    1.75
     anxious
    1.70
    Activations Density 0.023%

    No Known Activations