© 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. 12123
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and the legal system

    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
    2:0.03
    3:0.05
    4:0.07
    5:0.34
    6:0.02
    7:0.04
    8:0.02
    9:0.25
    10:0.02
    11:0.06
    Negative Logits
     suffice
    -2.87
     tended
    -2.81
     outnumbered
    -2.72
     lacked
    -2.63
     poorer
    -2.53
     richer
    -2.43
     unanimous
    -2.43
    Instead
    -2.41
    ]).
    -2.41
    Initialized
    -2.40
    POSITIVE LOGITS
    possibly
    2.98
    ivities
    2.66
    agraph
    2.54
     Exposure
    2.45
    ogens
    2.42
     Investigators
    2.32
    igate
    2.27
     potentially
    2.25
    oubt
    2.23
    cern
    2.22
    Activations Density 0.045%

    No Known Activations