© 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. 39491
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and themes related to human experiences and relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.03
    1:0.03
    2:0.17
    3:0.13
    4:0.19
    5:0.03
    6:0.05
    7:0.09
    8:0.05
    9:0.03
    10:0.08
    11:0.07
    Negative Logits
    eenth
    -1.66
    esson
    -1.48
     Recap
    -1.38
    gue
    -1.37
    otiation
    -1.35
     ASA
    -1.34
     Participant
    -1.33
    atta
    -1.32
     Ging
    -1.31
     PTS
    -1.30
    POSITIVE LOGITS
     brim
    1.68
    ificent
    1.67
     overflowing
    1.52
     colorful
    1.52
     boobs
    1.52
     sunshine
    1.50
     buzzing
    1.50
     tons
    1.46
     elegance
    1.43
     loving
    1.43
    Activations Density 0.011%

    No Known Activations