© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20354
    Prev
    Next
    INDEX
    Explanations

    references to social media engagement and following individuals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.03
    2:0.03
    3:0.03
    4:0.06
    5:0.10
    6:0.04
    7:0.04
    8:0.04
    9:0.18
    10:0.04
    11:0.32
    Negative Logits
     disg
    -2.50
     cherry
    -2.08
     clause
    -2.05
     testament
    -2.05
     fig
    -2.04
    #$
    -2.03
     estimating
    -1.95
     extingu
    -1.86
     Remem
    -1.86
     formula
    -1.82
    POSITIVE LOGITS
    outube
    2.95
     Posts
    2.66
    Twitter
    2.54
    blogs
    2.53
     Blog
    2.52
    folio
    2.47
     Twitter
    2.42
     blog
    2.41
     blogs
    2.41
     Forums
    2.39
    Activations Density 0.011%

    No Known Activations