© 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. 9-ATT-KK
    6. 21631
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong opinions or significant statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.13
    1:0.02
    2:0.05
    3:0.05
    4:0.04
    5:0.05
    6:0.14
    7:0.04
    8:0.23
    9:0.13
    10:0.03
    11:0.04
    Negative Logits
     Wen
    -3.65
    wen
    -3.65
     Kem
    -3.50
     PW
    -3.42
    WI
    -3.29
    eping
    -3.25
    wn
    -3.22
    Widget
    -3.22
    wick
    -3.21
     widget
    -3.14
    POSITIVE LOGITS
     Scala
    9.97
     Schwar
    4.93
     println
    4.54
     Scal
    4.37
     Dal
    4.21
     Castro
    4.11
     Clojure
    4.07
     Java
    4.05
     Garcia
    4.00
     steril
    3.91
    Activations Density 0.001%

    No Known Activations