© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6314
    Prev
    Next
    INDEX
    Explanations

    references to stability and support in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.04
    4:0.03
    5:0.04
    6:0.20
    7:0.04
    8:0.03
    9:0.29
    10:0.03
    11:0.03
    Negative Logits
     Cyp
    -3.91
    ippers
    -3.71
    ipper
    -3.62
    DATA
    -3.51
    ategory
    -3.42
     Piper
    -3.33
    ocaly
    -3.28
    Mem
    -3.27
     Melanie
    -3.20
    apeake
    -3.19
    POSITIVE LOGITS
     Stand
    7.24
     stand
    6.68
    stand
    6.37
     STAND
    6.15
    Stand
    6.01
     stands
    5.62
     standing
    5.49
    standing
    5.15
     stood
    4.90
     Standing
    4.71
    Activations Density 0.008%

    No Known Activations