© 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. 10-ATT-KK
    11. 15171
    Prev
    Next
    INDEX
    Explanations

    specific details related to timeframes and dates, particularly in the context of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.08
    3:0.36
    4:0.05
    5:0.03
    6:0.06
    7:0.09
    8:0.03
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    ·
    -2.87
    terday
    -2.56
     prin
    -2.55
    Obama
    -2.48
    STDOUT
    -2.46
    arious
    -2.33
    nings
    -2.32
    heid
    -2.32
     "$:/
    -2.30
    Reviewer
    -2.28
    POSITIVE LOGITS
     2019
    8.06
     2018
    7.88
    2018
    6.99
     2017
    6.19
     2020
    6.08
     2021
    6.03
    2019
    5.62
    2017
    5.58
     2022
    5.37
     2024
    5.31
    Activations Density 0.037%

    No Known Activations