© 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. 4308
    Prev
    Next
    INDEX
    Explanations

    terms related to exceptions and permissions in a legal or copyright context

    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
    0:0.09
    1:0.03
    2:0.08
    3:0.07
    4:0.03
    5:0.05
    6:0.22
    7:0.05
    8:0.08
    9:0.17
    10:0.03
    11:0.04
    Negative Logits
    Motor
    -3.89
    Param
    -3.81
     Hatt
    -3.80
    >[
    -3.75
     ashore
    -3.47
     Spit
    -3.44
     Paran
    -3.43
     roadside
    -3.39
     beach
    -3.37
     Tobacco
    -3.33
    POSITIVE LOGITS
     cube
    9.29
     Cube
    9.00
     cubes
    8.70
     Cub
    8.05
    Cub
    7.47
    cube
    6.78
    Cube
    6.74
     cub
    6.36
     Zub
    4.40
     Minotaur
    4.32
    Activations Density 0.003%

    No Known Activations