© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 11876
    Prev
    Next
    INDEX
    Explanations

    references to specific time frames and their significance in a narrative context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.03
    3:0.04
    4:0.04
    5:0.15
    6:0.01
    7:0.02
    8:0.01
    9:0.59
    10:0.01
    11:0.03
    Negative Logits
    igible
    -2.09
    ACTED
    -2.07
    icable
    -2.05
    ouf
    -2.00
    posure
    -1.99
    rival
    -1.98
    connected
    -1.97
    ◼
    -1.93
    Favorite
    -1.92
    SPONSORED
    -1.90
    POSITIVE LOGITS
     by
    5.70
    by
    4.92
     By
    4.14
    By
    4.03
     BY
    3.81
    bys
    2.54
     via
    2.36
    BY
    2.32
     through
    2.20
    Enlarge
    2.17
    Activations Density 1.461%

    No Known Activations