© 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. 38260
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "s."

    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
    0:0.01
    1:0.01
    2:0.21
    3:0.09
    4:0.04
    5:0.06
    6:0.21
    7:0.12
    8:0.07
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
    fulness
    -1.72
    icide
    -1.60
     seriousness
    -1.58
    urance
    -1.47
     indiscrim
    -1.41
     drowning
    -1.40
     dearly
    -1.37
     fabric
    -1.37
     headache
    -1.37
     exaggerated
    -1.35
    POSITIVE LOGITS
    thouse
    1.83
    ibo
    1.70
    amia
    1.58
    ilater
    1.52
    ovember
    1.46
    oard
    1.45
    GROUP
    1.43
    alore
    1.43
    Oak
    1.41
    EVA
    1.38
    Activations Density 0.007%

    No Known Activations