© 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. 12728
    Prev
    Next
    INDEX
    Explanations

    email addresses containing "gmail.com" and "yahoo.com"

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

    email addresses

    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
    0:0.01
    1:0.05
    2:0.09
    3:0.13
    4:0.02
    5:0.04
    6:0.10
    7:0.12
    8:0.09
    9:0.09
    10:0.11
    11:0.09
    Negative Logits
    inav
    -1.36
    SPONSORED
    -1.26
     Mub
    -1.00
     eyebrow
    -0.97
    kef
    -0.96
     Chau
    -0.96
     GOODMAN
    -0.95
     ultras
    -0.92
     transgender
    -0.91
    eele
    -0.90
    POSITIVE LOGITS
    iban
    1.15
    issues
    1.09
    cffff
    1.06
    theless
    1.02
    ertodd
    0.99
     Logged
    0.98
    deck
    0.97
    igi
    0.91
    boss
    0.90
    cci
    0.88
    Activations Density 0.004%

    No Known Activations