© 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. 12877
    Prev
    Next
    INDEX
    Explanations

    tokens that indicate structure and relationships in text, particularly focusing on conjunctions and logical operators

    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
    0:0.05
    1:0.04
    2:0.03
    3:0.03
    4:0.06
    5:0.02
    6:0.09
    7:0.39
    8:0.04
    9:0.04
    10:0.04
    11:0.11
    Negative Logits
     Borough
    -2.83
     Dow
    -2.78
     dish
    -2.75
    ecake
    -2.61
     butter
    -2.52
    ocol
    -2.51
     TY
    -2.51
     dishes
    -2.50
     borough
    -2.46
     Schultz
    -2.43
    POSITIVE LOGITS
    illin
    2.87
    externalActionCode
    2.86
    rahim
    2.75
    Allen
    2.73
    avi
    2.72
    Roaming
    2.71
    fml
    2.67
    ANG
    2.64
     ISIL
    2.64
     Keane
    2.63
    Activations Density 0.004%

    No Known Activations