© 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. 10-ATT-KK
    11. 20821
    Prev
    Next
    INDEX
    Explanations

    conversations involving notable questions or queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.09
    2:0.09
    3:0.04
    4:0.04
    5:0.03
    6:0.07
    7:0.09
    8:0.03
    9:0.04
    10:0.15
    11:0.06
    Negative Logits
     Strongh
    -3.51
     TCU
    -3.19
    FO
    -3.06
     Romero
    -2.88
     Forge
    -2.87
     Warp
    -2.85
     Goat
    -2.82
     Pork
    -2.82
     worm
    -2.80
     Worm
    -2.78
    POSITIVE LOGITS
     lithium
    9.49
     Lith
    7.93
     batteries
    5.19
     bipolar
    5.11
    Li
    4.92
     electroly
    4.90
     battery
    4.69
     magnesium
    4.66
     Li
    4.43
    Battery
    4.34
    Activations Density 0.003%

    No Known Activations