© 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. 10-ATT-KK
    11. 6695
    Prev
    Next
    INDEX
    Explanations

    statements about actions or commands related to provisioning or creating something

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.14
    1:0.10
    2:0.07
    3:0.07
    4:0.04
    5:0.03
    6:0.12
    7:0.11
    8:0.05
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     Wyn
    -3.14
     Lua
    -3.03
     Wy
    -2.97
    Lua
    -2.97
     Gaga
    -2.96
     Huck
    -2.95
     Akin
    -2.95
    lua
    -2.93
    itsch
    -2.93
     Slug
    -2.87
    POSITIVE LOGITS
     partitions
    6.01
     partition
    5.96
     divid
    2.93
     separation
    2.88
     detach
    2.80
    adata
    2.78
     evict
    2.77
    separ
    2.73
     intervals
    2.72
     contiguous
    2.72
    Activations Density 0.000%

    No Known Activations