© 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. 24178
    Prev
    Next
    INDEX
    Explanations

    numerical data or figures related to computing or system performance

    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
    0:0.11
    1:0.05
    2:0.05
    3:0.14
    4:0.05
    5:0.15
    6:0.10
    7:0.05
    8:0.06
    9:0.10
    10:0.05
    11:0.05
    Negative Logits
     Khe
    -2.62
     Vet
    -2.61
     Schne
    -2.61
     Tumblr
    -2.55
     nep
    -2.51
     Howe
    -2.50
    Anth
    -2.45
     NK
    -2.36
     Chap
    -2.33
     Chrys
    -2.32
    POSITIVE LOGITS
    tx
    2.71
    Driver
    2.66
    drivers
    2.65
     OpenGL
    2.63
     Driver
    2.60
     Utilities
    2.58
     drivers
    2.57
    draw
    2.54
     Drivers
    2.50
    gpu
    2.47
    Activations Density 0.011%

    No Known Activations