© 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. 19279
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and statistical data related to societal issues

    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
    1:0.04
    2:0.28
    3:0.04
    4:0.11
    5:0.05
    6:0.04
    7:0.15
    8:0.07
    9:0.08
    10:0.02
    11:0.05
    Negative Logits
    acio
    -2.81
    Synopsis
    -2.68
    :{
    -2.61
    ゴン
    -2.55
    Contents
    -2.52
    enda
    -2.50
    ��
    -2.47
    ワン
    -2.45
    .#
    -2.36
     coord
    -2.30
    POSITIVE LOGITS
     83
    4.42
     63
    4.35
     73
    4.33
     57
    4.31
     43
    4.31
     67
    4.25
     33
    4.22
     44
    4.19
     62
    4.16
     37
    4.14
    Activations Density 0.126%

    No Known Activations