© 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. 11783
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the form "Month Day, Year" within the text

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

    dates and numerical data in texts

    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
    0:0.02
    1:0.30
    2:0.07
    3:0.09
    4:0.03
    5:0.05
    6:0.07
    7:0.06
    8:0.06
    9:0.10
    10:0.06
    11:0.05
    Negative Logits
     jaws
    -1.42
     robbers
    -1.36
     expansions
    -1.32
     balloon
    -1.32
     inspectors
    -1.31
     parasitic
    -1.29
     Nationwide
    -1.29
     Hearts
    -1.28
     bumps
    -1.27
     Canaver
    -1.25
    POSITIVE LOGITS
    )</
    1.94
    olitics
    1.90
    uminati
    1.78
    np
    1.73
    rad
    1.70
    RG
    1.67
    TOR
    1.64
    CBC
    1.61
    _
    1.53
    anqu
    1.52
    Activations Density 0.038%

    No Known Activations