© 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. 12818
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to statistics

    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
    0:0.09
    1:0.11
    2:0.08
    3:0.04
    4:0.07
    5:0.05
    6:0.04
    7:0.08
    8:0.13
    9:0.06
    10:0.14
    11:0.05
    Negative Logits
    YC
    -3.19
     Snake
    -3.10
    Snake
    -3.03
     Rosenberg
    -2.97
    Python
    -2.49
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    -2.49
     Knife
    -2.49
     Andromeda
    -2.42
     Mori
    -2.39
     Pengu
    -2.37
    POSITIVE LOGITS
    hap
    3.10
     van
    3.06
    ijk
    2.99
    vier
    2.79
    wark
    2.76
    ewitness
    2.69
    ijn
    2.62
    hew
    2.57
    ver
    2.48
    amins
    2.47
    Activations Density 0.011%

    No Known Activations