© 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. 10-ATT-KK
    11. 22307
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that represent certain entities, possibly names or designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.16
    1:0.24
    2:0.03
    3:0.04
    4:0.04
    5:0.02
    6:0.07
    7:0.11
    8:0.03
    9:0.03
    10:0.15
    11:0.04
    Negative Logits
     OU
    -3.00
     Arn
    -2.63
     Omega
    -2.62
     geared
    -2.54
    Rad
    -2.47
     Tray
    -2.46
     Bonnie
    -2.43
    Jar
    -2.43
     Kin
    -2.40
     Trin
    -2.37
    POSITIVE LOGITS
    aff
    3.50
    cffff
    3.25
    fff
    3.24
    endez
    3.20
    aucus
    3.06
    ffe
    3.00
    ff
    2.94
    ffff
    2.91
    FF
    2.84
    affe
    2.83
    Activations Density 0.001%

    No Known Activations