© 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. 12837
    Prev
    Next
    INDEX
    Explanations

    text enclosed in quotation marks

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

    occurrences of quotation marks and apostrophes

    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
    0:0.08
    1:0.04
    2:0.05
    3:0.04
    4:0.32
    5:0.07
    6:0.09
    7:0.04
    8:0.04
    9:0.04
    10:0.09
    11:0.04
    Negative Logits
    soDeliveryDate
    -2.45
    hler
    -1.74
    uctor
    -1.63
    ioxide
    -1.58
    owl
    -1.56
    uther
    -1.51
    stood
    -1.50
     sshd
    -1.46
    rontal
    -1.46
    dinand
    -1.45
    POSITIVE LOGITS
    ?'"
    2.22
    .'"
    2.14
    ]'
    2.05
    '"
    1.97
    stellar
    1.95
    '."
    1.91
    ]."
    1.89
     '.
    1.87
     ‎
    1.85
    !'"
    1.83
    Activations Density 0.006%

    No Known Activations