© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9184
    Prev
    Next
    INDEX
    Explanations

    references to ratings or scores

    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
    2:0.06
    3:0.03
    4:0.05
    5:0.06
    6:0.31
    7:0.05
    8:0.04
    9:0.19
    10:0.03
    11:0.05
    Negative Logits
     Garrison
    -4.11
    Nap
    -3.83
     Yao
    -3.79
     Ober
    -3.69
     Kang
    -3.58
     Oy
    -3.56
     Ham
    -3.54
     Schwar
    -3.54
     Qian
    -3.53
     Nau
    -3.53
    POSITIVE LOGITS
     DR
    8.95
    DR
    7.67
    dr
    6.31
    Dri
    4.34
     dr
    4.09
    Driver
    4.04
     DRM
    3.98
    dri
    3.97
    Dr
    3.93
    drivers
    3.92
    Activations Density 0.001%

    No Known Activations