© 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. 17405
    Prev
    Next
    INDEX
    Explanations

    references to various forms of measurement and evaluation in contexts such as physics and social behaviors

    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
    0:0.03
    1:0.02
    2:0.06
    3:0.04
    4:0.07
    5:0.50
    6:0.02
    7:0.03
    8:0.02
    9:0.11
    10:0.02
    11:0.04
    Negative Logits
     REALLY
    -3.69
    very
    -3.46
     Definitely
    -3.41
    really
    -3.36
     definitely
    -3.30
     really
    -3.20
    initely
    -3.18
    Very
    -3.16
     absolutely
    -3.09
     Really
    -3.08
    POSITIVE LOGITS
     when
    3.21
     lest
    3.03
     insofar
    2.92
     unless
    2.75
     since
    2.71
     until
    2.65
     while
    2.54
     whenever
    2.54
     because
    2.54
    SPONSORED
    2.49
    Activations Density 0.385%

    No Known Activations