© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 17205
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases indicating reference points or commands in text

    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
    0:0.06
    1:0.04
    2:0.07
    3:0.03
    4:0.05
    5:0.04
    6:0.19
    7:0.04
    8:0.05
    9:0.31
    10:0.02
    11:0.04
    Negative Logits
    ITNESS
    -3.89
     Gree
    -3.77
     Ree
    -3.72
    isSpecialOrderable
    -3.64
     Wiggins
    -3.51
    joy
    -3.49
    GRE
    -3.36
    gres
    -3.34
     Gerrard
    -3.33
     Roku
    -3.30
    POSITIVE LOGITS
    Ant
    8.78
     Ant
    8.51
     ant
    7.51
     ants
    7.03
     Anton
    6.64
    ANT
    6.46
     Antar
    5.89
     Anthem
    5.63
     antip
    5.51
    ant
    5.37
    Activations Density 0.024%

    No Known Activations