© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41169
    Prev
    Next
    INDEX
    Explanations

    references to news organizations and foundations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.11
    3:0.04
    4:0.03
    5:0.02
    6:0.18
    7:0.07
    8:0.04
    9:0.04
    10:0.29
    11:0.09
    Negative Logits
     Inferno
    -1.66
     Grind
    -1.66
     Mahjong
    -1.61
     Samurai
    -1.59
    terness
    -1.53
     smoker
    -1.53
     Spani
    -1.46
     Hitchcock
    -1.44
     GTA
    -1.43
     Mazda
    -1.43
    POSITIVE LOGITS
    foundation
    1.88
    affiliated
    1.70
     finance
    1.62
    anners
    1.59
     livest
    1.59
    funded
    1.58
    managed
    1.58
    leaders
    1.56
    financial
    1.56
     skelet
    1.55
    Activations Density 0.001%

    No Known Activations