© 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. 10-ATT-KK
    11. 6760
    Prev
    Next
    INDEX
    Explanations

    references to Instagram-related accounts and activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.18
    1:0.03
    2:0.12
    3:0.07
    4:0.04
    5:0.02
    6:0.08
    7:0.18
    8:0.01
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    awaru
    -2.67
     Randolph
    -2.60
     CRC
    -2.58
     Zel
    -2.44
    ulhu
    -2.36
     Tacoma
    -2.34
     Lovecraft
    -2.33
    Sov
    -2.30
     Cthulhu
    -2.21
    Rand
    -2.18
    POSITIVE LOGITS
     Instagram
    5.54
     Snapchat
    5.23
     Instr
    3.49
     hasht
    3.49
    Snap
    3.41
     selfie
    3.39
     WhatsApp
    3.34
     Pinterest
    3.23
     Flickr
    3.16
     Pic
    3.10
    Activations Density 0.017%

    No Known Activations