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. 2-ATT-KK
    6. 22240
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    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
    2:0.28
    3:0.05
    4:0.03
    5:0.04
    6:0.02
    7:0.01
    8:0.27
    9:0.12
    10:0.04
    11:0.01
    Negative Logits
    arov
    -1.28
    ONSORED
    -1.26
    ynski
    -1.25
    ウス
    -1.25
     guessed
    -1.22
     ove
    -1.21
     efforts
    -1.19
    eele
    -1.19
    heny
    -1.18
     attempts
    -1.15
    POSITIVE LOGITS
    DragonMagazine
    1.33
     Jungle
    1.25
    版
    1.21
    rete
    1.21
     Billboard
    1.19
    advertisement
    1.18
    itaire
    1.17
     runway
    1.16
    mares
    1.15
     Gauntlet
    1.15
    Activations Density 0.030%

    No Known Activations