© 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. 33249
    Prev
    Next
    INDEX
    Explanations

    instances of hashtags and social media handles

    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
    0:0.04
    1:0.03
    2:0.08
    3:0.06
    4:0.10
    5:0.03
    6:0.12
    7:0.08
    8:0.12
    9:0.04
    10:0.08
    11:0.18
    Negative Logits
     Brigade
    -1.55
     Mane
    -1.50
    achine
    -1.41
     Playoffs
    -1.32
     Royale
    -1.29
     fandom
    -1.24
     legend
    -1.24
     organizing
    -1.24
     semantic
    -1.23
     fest
    -1.22
    POSITIVE LOGITS
    INGS
    1.58
    ridges
    1.50
    Damage
    1.44
    Effects
    1.43
    Ther
    1.38
    orgetown
    1.38
    Compl
    1.35
    Policy
    1.34
    Changes
    1.32
    Director
    1.30
    Activations Density 0.001%

    No Known Activations