© 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. 9-ATT-KK
    11. 5760
    Prev
    Next
    INDEX
    Explanations

    negative statements or phrases indicating difficulty or impossibility

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.36
    1:0.04
    2:0.12
    3:0.07
    4:0.04
    5:0.05
    6:0.04
    7:0.06
    8:0.03
    9:0.03
    10:0.08
    11:0.03
    Negative Logits
     shorts
    -2.49
     Eag
    -2.35
     forwarding
    -2.31
    ilater
    -2.27
     cereal
    -2.13
    geist
    -2.13
    arlane
    -2.12
     invests
    -2.11
     departed
    -2.10
     Values
    -2.09
    POSITIVE LOGITS
     hardest
    2.84
     toughest
    2.81
     tougher
    2.72
     harder
    2.68
     easier
    2.64
    Easy
    2.62
     grinding
    2.58
     Difficulty
    2.53
    easy
    2.50
     hardness
    2.49
    Activations Density 0.078%

    No Known Activations