© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12135
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and personal histories

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

    references to familial relationships and ancestry

    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
    0:0.04
    1:0.06
    2:0.17
    3:0.10
    4:0.03
    5:0.04
    6:0.12
    7:0.11
    8:0.09
    9:0.03
    10:0.08
    11:0.09
    Negative Logits
     rake
    -1.02
     neocons
    -0.98
     orbit
    -0.97
     neutrality
    -0.96
     Balk
    -0.95
    Aren
    -0.94
     objective
    -0.94
     hole
    -0.92
     Scorp
    -0.92
    Fall
    -0.90
    POSITIVE LOGITS
    reprene
    1.29
    tein
    1.28
    reated
    1.21
    ashtra
    1.21
    achel
    1.19
    aternal
    1.19
    iesel
    1.18
    laughter
    1.15
    inct
    1.15
    utics
    1.15
    Activations Density 0.039%

    No Known Activations