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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15102
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate connection or continuity in thoughts

    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
    0:0.11
    1:0.08
    2:0.08
    3:0.07
    4:0.07
    5:0.05
    6:0.08
    7:0.07
    8:0.07
    9:0.08
    10:0.12
    11:0.08
    Negative Logits
     Abel
    -3.43
     Ald
    -3.04
     MARK
    -2.96
     [/
    -2.92
     ALE
    -2.78
    apest
    -2.74
     mk
    -2.73
     AB
    -2.71
     Bord
    -2.68
     Meredith
    -2.67
    POSITIVE LOGITS
     Doodle
    6.32
     Dota
    3.49
     donkey
    3.24
    Widget
    3.06
     sprite
    3.01
     Gan
    3.00
    Pokemon
    2.98
     sprites
    2.98
     Hover
    2.97
     Dough
    2.94
    Activations Density 0.000%

    No Known Activations