© 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. 39469
    Prev
    Next
    INDEX
    Explanations

    references to body reactions and gut-related terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.04
    2:0.04
    3:0.04
    4:0.04
    5:0.04
    6:0.38
    7:0.09
    8:0.03
    9:0.06
    10:0.13
    11:0.04
    Negative Logits
    イト
    -1.65
    arcity
    -1.57
    Downloadha
    -1.42
    KK
    -1.40
    ドラ
    -1.38
    jad
    -1.38
    JA
    -1.35
    bucks
    -1.34
    license
    -1.32
    BTC
    -1.30
    POSITIVE LOGITS
     Peck
    1.38
     rh
    1.29
     bladder
    1.25
     Thatcher
    1.22
     Staten
    1.21
     gut
    1.20
     Gupta
    1.18
    sand
    1.18
     Berman
    1.18
     beh
    1.17
    Activations Density 0.001%

    No Known Activations