© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 27237
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.11
    3:0.11
    4:0.16
    5:0.06
    6:0.13
    7:0.09
    8:0.05
    9:0.08
    10:0.07
    11:0.04
    Negative Logits
     Fas
    -1.27
     Nickel
    -1.26
     Loll
    -1.22
     Tud
    -1.15
     Crunch
    -1.15
     daytime
    -1.07
     Frem
    -1.06
     informal
    -1.06
     Pom
    -1.05
     nationally
    -1.05
    POSITIVE LOGITS
    _>
    1.68
    hop
    1.29
    ヘラ
    1.28
    skip
    1.26
    EStream
    1.24
    akov
    1.22
    ockets
    1.20
    ettel
    1.20
    irus
    1.19
    desc
    1.18
    Activations Density 0.012%

    No Known Activations