© 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. 6489
    Prev
    Next
    INDEX
    Explanations

    concepts related to discontinuous technological progress

    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
    0:0.07
    1:0.28
    2:0.07
    3:0.08
    4:0.05
    5:0.02
    6:0.08
    7:0.10
    8:0.02
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
    akedown
    -2.73
     Hog
    -2.73
    doors
    -2.58
    agy
    -2.48
    uliffe
    -2.44
    hoe
    -2.42
     Rim
    -2.36
    irtual
    -2.35
    agall
    -2.34
    Bad
    -2.33
    POSITIVE LOGITS
     Continuous
    5.70
     continuous
    5.22
     Contin
    4.50
    contin
    4.35
     intermittent
    4.30
    Contin
    4.22
     steady
    4.08
     intermitt
    3.79
     persistence
    3.78
     continual
    3.70
    Activations Density 0.023%

    No Known Activations