© 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. 16960
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 's'

    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
    0:0.03
    1:0.02
    2:0.19
    3:0.10
    4:0.04
    5:0.09
    6:0.22
    7:0.03
    8:0.03
    9:0.06
    10:0.05
    11:0.08
    Negative Logits
    tical
    -1.45
    acle
    -1.38
    bourg
    -1.34
    piece
    -1.31
    ocr
    -1.30
    ilk
    -1.27
     firefighter
    -1.26
    cock
    -1.25
     joke
    -1.25
     Hits
    -1.22
    POSITIVE LOGITS
    ovember
    1.42
     kindred
    1.42
    luaj
    1.36
     sidx
    1.35
    ratom
    1.34
    MpServer
    1.34
    anto
    1.31
     adjourn
    1.31
    dimension
    1.31
    neck
    1.30
    Activations Density 0.010%

    No Known Activations