© 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. 12726
    Prev
    Next
    INDEX
    Explanations

    phrases where directives or questions starting with "who" are used

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

    references to individuals or questions about personal identity

    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
    0:0.10
    1:0.04
    2:0.06
    3:0.04
    4:0.02
    5:0.06
    6:0.18
    7:0.05
    8:0.04
    9:0.05
    10:0.19
    11:0.10
    Negative Logits
    enegger
    -1.33
    aneous
    -1.25
    osure
    -1.23
    JM
    -1.19
    fired
    -1.16
    thur
    -1.15
    roximately
    -1.12
    ront
    -1.11
    ディ
    -1.09
    rin
    -1.08
    POSITIVE LOGITS
    pedia
    1.49
     informants
    1.28
     pronouns
    1.28
     aliases
    1.21
    chwitz
    1.21
     NPCs
    1.20
     Masquerade
    1.16
     dement
    1.15
    ipedia
    1.15
    heid
    1.13
    Activations Density 0.024%

    No Known Activations