© 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. 3-ATT-KK
    11. 12910
    Prev
    Next
    INDEX
    Explanations

    locations, names, and dates within biographical passages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to life experiences and personal journeys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.07
    2:0.05
    3:0.02
    4:0.06
    5:0.36
    6:0.04
    7:0.05
    8:0.05
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
    Interstitial
    -2.06
    %"
    -2.00
     takedown
    -1.98
    ggle
    -1.89
    seless
    -1.88
     bullshit
    -1.82
     disag
    -1.78
    hide
    -1.78
    mite
    -1.77
     spam
    -1.76
    POSITIVE LOGITS
     Married
    2.46
    alysed
    2.12
     Born
    1.98
    ominium
    1.97
    married
    1.97
    irlf
    1.95
     married
    1.91
     heirs
    1.91
     lifelong
    1.86
     ordained
    1.85
    Activations Density 0.167%

    No Known Activations