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. 20626
    Prev
    Next
    INDEX
    Explanations

    connections between circadian rhythms and metabolic processes

    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
    0:0.17
    1:0.03
    2:0.19
    3:0.10
    4:0.05
    5:0.09
    6:0.06
    7:0.07
    8:0.08
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    Beer
    -2.89
     burger
    -2.78
     Manziel
    -2.75
     sauces
    -2.64
    merga
    -2.63
    iquette
    -2.63
    alty
    -2.63
    igun
    -2.61
     pour
    -2.60
     fries
    -2.54
    POSITIVE LOGITS
     REM
    4.02
     synchron
    4.01
     circadian
    3.93
     synchronization
    3.77
    REM
    3.56
     synchronized
    3.55
    atonin
    3.51
     clock
    3.43
     rhythms
    3.42
     clocks
    3.16
    Activations Density 0.012%

    No Known Activations