© 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. 19332
    Prev
    Next
    INDEX
    Explanations

    negated forms of verbs and contractions indicating absence or incapacity

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.06
    4:0.03
    5:0.02
    6:0.08
    7:0.02
    8:0.03
    9:0.05
    10:0.04
    11:0.52
    Negative Logits
     Pegasus
    -2.57
     Hercules
    -2.55
     favour
    -2.38
     recognised
    -2.37
     JFK
    -2.32
     Forth
    -2.32
     Darwin
    -2.31
     Wichita
    -2.28
     fancy
    -2.23
     somew
    -2.22
    POSITIVE LOGITS
    |
    5.79
    ●
    5.48
    -|
    5.47
    −
    5.39
    ·
    5.38
    �
    5.25
     |
    5.18
    )|
    5.09
    .—
    5.01
    ■
    4.87
    Activations Density 0.867%

    No Known Activations