© 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. 13762
    Prev
    Next
    INDEX
    Explanations

    details about instructions and commands, particularly in technical 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
    1:0.05
    2:0.38
    3:0.07
    4:0.04
    5:0.05
    6:0.04
    7:0.06
    8:0.03
    9:0.07
    10:0.04
    11:0.01
    Negative Logits
     msec
    -2.64
    chron
    -2.46
     millisec
    -2.43
     fal
    -2.36
     WIN
    -2.35
     waged
    -2.31
     prevailing
    -2.29
     Teach
    -2.28
     prevail
    -2.27
     vantage
    -2.23
    POSITIVE LOGITS
     additions
    5.54
     Adding
    4.87
     added
    4.66
     adding
    4.60
     adds
    4.42
     add
    4.33
    Adding
    4.32
     additive
    4.12
    added
    4.09
     Add
    4.07
    Activations Density 0.181%

    No Known Activations