© 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. 5-ATT-KK
    11. 16751
    Prev
    Next
    INDEX
    Explanations

    dates and time-related events

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.12
    3:0.14
    4:0.07
    5:0.05
    6:0.02
    7:0.05
    8:0.10
    9:0.07
    10:0.17
    11:0.13
    Negative Logits
    uably
    -1.18
    ゴ
    -1.15
    htaking
    -1.14
    inous
    -1.13
    ubby
    -1.12
     dich
    -1.11
    wrong
    -1.08
    �
    -1.08
     effortlessly
    -1.07
    カ
    -1.05
    POSITIVE LOGITS
    morrow
    1.82
     expires
    1.54
     TBD
    1.45
     TBA
    1.45
     pending
    1.44
    ichever
    1.44
     adjourn
    1.43
    nesday
    1.41
     whichever
    1.40
     timetable
    1.36
    Activations Density 1.343%

    No Known Activations