© 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. 12019
    Prev
    Next
    INDEX
    Explanations

    phrases related to capability and comparisons in context to expertise or authority

    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
    1:0.31
    2:0.05
    3:0.05
    4:0.07
    5:0.04
    6:0.06
    7:0.08
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
     misunderstand
    -2.86
    omon
    -2.77
    orah
    -2.75
     badly
    -2.67
     Barron
    -2.64
     Frie
    -2.48
    ouver
    -2.47
    dayName
    -2.46
     indo
    -2.42
    opens
    -2.38
    POSITIVE LOGITS
     Absolute
    7.63
    absolute
    6.74
     absolute
    6.32
     Relative
    6.20
    relative
    5.71
     relative
    5.29
    Abs
    4.65
    olute
    3.38
    Rel
    3.27
    Ultimate
    3.23
    Activations Density 0.005%

    No Known Activations