© 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. 6538
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical symbols

    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
    0:0.17
    1:0.04
    2:0.08
    3:0.11
    4:0.10
    5:0.11
    6:0.03
    7:0.13
    8:0.05
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
     extr
    -2.27
     Extend
    -2.20
     Launcher
    -2.18
     folds
    -2.12
     casing
    -2.12
     Socket
    -2.10
    bol
    -2.07
     Spiral
    -2.03
     fold
    -1.99
     Folder
    -1.99
    POSITIVE LOGITS
    json
    2.20
    oddy
    2.10
    izzy
    2.09
    kw
    2.02
    atson
    2.02
    tnc
    1.99
    mounted
    1.98
    photo
    1.92
    Nat
    1.92
    uracy
    1.90
    Activations Density 0.001%

    No Known Activations