© 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. 12081
    Prev
    Next
    INDEX
    Explanations

    sports-related information such as team names and years

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

    statistical references and data points related to sports and economics

    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
    0:0.09
    1:0.06
    2:0.09
    3:0.05
    4:0.14
    5:0.08
    6:0.08
    7:0.07
    8:0.06
    9:0.04
    10:0.11
    11:0.06
    Negative Logits
    hyde
    -1.39
    stadt
    -1.10
    bart
    -1.09
    soever
    -1.05
    STE
    -1.04
     "$:/
    -1.03
    '?
    -1.03
    OUS
    -1.03
    WARE
    -1.02
    oided
    -1.01
    POSITIVE LOGITS
    KNOWN
    1.06
    aviour
    0.98
    Latin
    0.96
    pload
    0.95
    uma
    0.94
    killed
    0.94
     praying
    0.89
    ongyang
    0.88
    cial
    0.88
     malaria
    0.87
    Activations Density 0.011%

    No Known Activations