© 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. 6579
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of limitations or conditionality related to different subjects

    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
    1:0.03
    2:0.03
    3:0.05
    4:0.09
    5:0.06
    6:0.02
    7:0.06
    8:0.03
    9:0.35
    10:0.03
    11:0.16
    Negative Logits
     Its
    -2.71
     its
    -2.32
     Anger
    -2.21
    rower
    -2.11
     Discipline
    -1.94
    spection
    -1.92
     resignation
    -1.90
     Orchestra
    -1.88
     hike
    -1.85
     Debate
    -1.83
    POSITIVE LOGITS
     ones
    3.49
    they
    3.30
     equivalents
    3.18
    their
    3.17
     prototypes
    3.04
    They
    3.01
     replacements
    2.99
     hybrids
    2.93
    them
    2.92
     them
    2.78
    Activations Density 0.666%

    No Known Activations