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

    Neuronpedia

    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. 36072
    Prev
    Next
    INDEX
    Explanations

    symbols or characters that represent formatting issues or errors

    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
    0:0.04
    1:0.02
    2:0.05
    3:0.08
    4:0.14
    5:0.03
    6:0.21
    7:0.02
    8:0.08
    9:0.08
    10:0.11
    11:0.09
    Negative Logits
     Ivory
    -1.19
     PLA
    -1.15
     Ct
    -1.11
     Jah
    -1.11
     spark
    -1.10
     indu
    -1.09
     LS
    -1.08
     MTV
    -1.07
     NCT
    -1.07
     Vu
    -1.07
    POSITIVE LOGITS
    livious
    1.37
    irs
    1.33
    translation
    1.27
    ouf
    1.25
    tags
    1.25
    Others
    1.21
    Pack
    1.21
    livion
    1.19
    added
    1.19
    offensive
    1.18
    Activations Density 0.009%

    No Known Activations