© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15279
    Prev
    Next
    INDEX
    Explanations

    references to research studies and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.03
    2:0.05
    3:0.08
    4:0.06
    5:0.27
    6:0.02
    7:0.04
    8:0.02
    9:0.29
    10:0.02
    11:0.04
    Negative Logits
    ?).
    -3.18
    ?),
    -3.14
    ?)
    -2.83
    !),
    -2.73
    !).
    -2.60
    )?
    -2.46
    !)
    -2.35
     quicker
    -2.34
     :(
    -2.33
     decay
    -2.31
    POSITIVE LOGITS
     originally
    2.36
     congratulations
    2.10
    empl
    2.08
    ascript
    2.07
    Interested
    2.03
    Originally
    2.01
     original
    2.01
     consulted
    1.99
     "'
    1.98
    ferred
    1.97
    Activations Density 0.006%

    No Known Activations