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. 5-ATT-KK
    6. 44182
    Prev
    Next
    INDEX
    Explanations

    occurrences of the articles "a" and "the"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.04
    4:0.19
    5:0.03
    6:0.19
    7:0.16
    8:0.03
    9:0.02
    10:0.10
    11:0.08
    Negative Logits
    edly
    -1.54
     arrang
    -1.48
    �
    -1.44
     acknow
    -1.43
     acknowled
    -1.36
    GES
    -1.36
     obliged
    -1.28
    POL
    -1.28
    SHIP
    -1.28
     explan
    -1.28
    POSITIVE LOGITS
     opponent
    1.74
     opponents
    1.59
    rival
    1.52
    itans
    1.42
    enemy
    1.35
     Playoff
    1.33
    Prim
    1.32
     rival
    1.31
     rivals
    1.29
     Warriors
    1.29
    Activations Density 0.010%

    No Known Activations