© 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. 47152
    Prev
    Next
    INDEX
    Explanations

    references to cardiovascular disease and its dietary influences

    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
    0:0.13
    1:0.07
    2:0.06
    3:0.05
    4:0.06
    5:0.06
    6:0.10
    7:0.02
    8:0.07
    9:0.09
    10:0.07
    11:0.17
    Negative Logits
     subtitles
    -1.49
     annex
    -1.49
    tones
    -1.47
    ック
    -1.43
     diplomatic
    -1.43
    cens
    -1.42
     nec
    -1.38
     grave
    -1.37
     FALSE
    -1.37
     Syndicate
    -1.35
    POSITIVE LOGITS
     Lastly
    1.50
     thus
    1.46
     Finally
    1.37
    versely
    1.36
    uberty
    1.36
    ivably
    1.35
     Typically
    1.32
     Meier
    1.32
     Quartz
    1.30
     Thus
    1.30
    Activations Density 0.001%

    No Known Activations