© 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. 47202
    Prev
    Next
    INDEX
    Explanations

    variations of the character "l" or its diacritical forms

    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
    2:0.16
    3:0.09
    4:0.09
    5:0.04
    6:0.27
    7:0.03
    8:0.05
    9:0.05
    10:0.07
    11:0.05
    Negative Logits
     uncond
    -1.45
     wilderness
    -1.27
     playground
    -1.25
     AAA
    -1.21
     Olympics
    -1.21
     operation
    -1.19
     hairc
    -1.18
     miscarriage
    -1.18
     servicing
    -1.16
     untouched
    -1.15
    POSITIVE LOGITS
    emort
    1.85
    inarily
    1.85
    ️
    1.83
    actionDate
    1.76
    ivably
    1.65
     WATCHED
    1.55
    obin
    1.53
    verified
    1.52
    vor
    1.49
    urations
    1.45
    Activations Density 0.032%

    No Known Activations