© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20327
    Prev
    Next
    INDEX
    Explanations

    phrases indicating accountability or statements of defense in communication contexts

    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
    0:0.10
    1:0.03
    2:0.06
    3:0.03
    4:0.05
    5:0.04
    6:0.23
    7:0.05
    8:0.05
    9:0.25
    10:0.02
    11:0.05
    Negative Logits
     hail
    -4.05
     Hail
    -3.96
    asar
    -3.73
     Starship
    -3.50
    icans
    -3.43
    arius
    -3.41
    083
    -3.36
     herpes
    -3.33
    icus
    -3.29
    assis
    -3.28
    POSITIVE LOGITS
     Powell
    10.87
    owell
    5.84
     Peb
    4.34
     Colin
    4.33
     Phelps
    4.32
     Pow
    4.21
     Pound
    4.05
     POW
    3.95
     Mills
    3.95
     Wool
    3.90
    Activations Density 0.002%

    No Known Activations