© 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. 10-ATT-KK
    11. 10106
    Prev
    Next
    INDEX
    Explanations

    dates and numerical identifiers related to events or publications

    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
    0:0.02
    1:0.02
    2:0.37
    3:0.08
    4:0.14
    5:0.05
    6:0.03
    7:0.04
    8:0.07
    9:0.06
    10:0.04
    11:0.02
    Negative Logits
    GPU
    -2.71
    Pokemon
    -2.69
    Pixel
    -2.62
    Column
    -2.57
    Pand
    -2.57
    BOX
    -2.51
    Marg
    -2.45
    Station
    -2.45
    Prim
    -2.43
    WAR
    -2.42
    POSITIVE LOGITS
     02
    4.63
     06
    4.51
     08
    4.26
     07
    4.24
     01
    4.21
     03
    4.14
     04
    3.96
     05
    3.89
     09
    3.84
     00
    3.62
    Activations Density 0.006%

    No Known Activations