© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    verbs that convey states of being or actions in various tenses

    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
    0:0.35
    1:0.10
    2:0.04
    3:0.04
    4:0.02
    5:0.11
    6:0.02
    7:0.02
    8:0.10
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
    onyms
    -2.11
    EStream
    -2.09
    eph
    -2.06
    rued
    -1.83
    venant
    -1.77
    etime
    -1.76
    oufl
    -1.73
    ihad
    -1.71
    ute
    -1.67
    onym
    -1.59
    POSITIVE LOGITS
     finding
    2.07
     wanting
    2.02
     noticing
    2.01
     shutting
    2.00
     shifting
    2.00
     gearing
    1.90
     getting
    1.87
     treating
    1.85
     tightening
    1.85
     stopping
    1.85
    Activations Density 0.071%

    No Known Activations