© 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. 22931
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement activities and related materials, such as weapons and counterfeit items

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.02
    2:0.03
    3:0.06
    4:0.13
    5:0.24
    6:0.03
    7:0.05
    8:0.01
    9:0.27
    10:0.02
    11:0.05
    Negative Logits
     Dhabi
    -2.71
     Flavoring
    -2.63
    reprene
    -2.57
     succeeds
    -2.50
    umph
    -2.50
    oppable
    -2.45
     Conserv
    -2.40
    appiness
    -2.37
    atorium
    -2.34
     endeavour
    -2.33
    POSITIVE LOGITS
     contained
    3.68
     taped
    3.44
     included
    3.06
    had
    3.05
     dated
    3.05
     smelled
    3.05
     belonged
    3.02
     totaling
    2.94
     stored
    2.91
     totaled
    2.80
    Activations Density 0.217%

    No Known Activations