© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 6623
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.03
    2:0.11
    3:0.08
    4:0.14
    5:0.04
    6:0.03
    7:0.22
    8:0.05
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    PLIED
    -1.68
    igation
    -1.42
    topic
    -1.39
     Philosophy
    -1.39
     Writing
    -1.38
    blade
    -1.37
    }{
    -1.36
    question
    -1.31
    黒
    -1.30
    examination
    -1.29
    POSITIVE LOGITS
    lier
    1.97
     condos
    1.75
     DJs
    1.65
     Sonny
    1.63
     incumb
    1.58
     taller
    1.54
     fitt
    1.47
     horizont
    1.46
    lishes
    1.43
     tallest
    1.42
    Activations Density 0.000%

    No Known Activations