© 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. 47250
    Prev
    Next
    INDEX
    Explanations

    references to duality or multiple options

    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
    0:0.04
    1:0.02
    2:0.12
    3:0.05
    4:0.10
    5:0.03
    6:0.33
    7:0.04
    8:0.05
    9:0.04
    10:0.07
    11:0.05
    Negative Logits
     Accessed
    -1.94
     Attempt
    -1.35
     Compatibility
    -1.31
    Choice
    -1.31
    enment
    -1.29
     Response
    -1.29
    assetsadobe
    -1.28
     Chall
    -1.28
     Moonlight
    -1.27
    quartered
    -1.25
    POSITIVE LOGITS
    henko
    1.80
    ETH
    1.71
    etti
    1.41
     pronoun
    1.38
    utive
    1.37
    bass
    1.37
    田
    1.31
     Spears
    1.30
    UTE
    1.29
     Bout
    1.29
    Activations Density 0.001%

    No Known Activations