© 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. 38220
    Prev
    Next
    INDEX
    Explanations

    the concept of keys and access in various contexts

    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
    0:0.01
    1:0.01
    2:0.07
    3:0.05
    4:0.09
    5:0.04
    6:0.05
    7:0.35
    8:0.02
    9:0.03
    10:0.17
    11:0.05
    Negative Logits
    govtrack
    -2.26
    assetsadobe
    -1.87
    Charges
    -1.83
    IRD
    -1.66
    ドラゴン
    -1.65
    REF
    -1.64
     ridicule
    -1.63
     Flavoring
    -1.63
    Ranked
    -1.61
     behavi
    -1.59
    POSITIVE LOGITS
     Genie
    1.92
     keys
    1.87
     Downing
    1.75
     levers
    1.71
    wagen
    1.68
     pi
    1.66
    Exit
    1.60
    igsaw
    1.60
    riger
    1.59
     unlocking
    1.58
    Activations Density 0.001%

    No Known Activations