© 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. 5-ATT-KK
    11. 24858
    Prev
    Next
    INDEX
    Explanations

    phrases that imply assessment or evaluation of situations, actions, or characteristics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.20
    3:0.27
    4:0.10
    5:0.03
    6:0.05
    7:0.05
    8:0.05
    9:0.07
    10:0.07
    11:0.03
    Negative Logits
     Confederation
    -1.43
     Nether
    -1.42
    berus
    -1.40
     accompanying
    -1.38
    espie
    -1.35
     Slater
    -1.34
     reins
    -1.29
     Byrne
    -1.27
     Haas
    -1.26
     Universities
    -1.26
    POSITIVE LOGITS
     crap
    1.64
     didnt
    1.62
    "]=>
    1.59
     REALLY
    1.59
     doesnt
    1.59
    !!!!!
    1.56
    love
    1.52
     dont
    1.52
     bitch
    1.52
     shit
    1.50
    Activations Density 0.010%

    No Known Activations