© 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. 10-ATT-KK
    11. 12368
    Prev
    Next
    INDEX
    Explanations

    references to legal decisions and governmental actions

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.11
    4:0.41
    5:0.09
    6:0.03
    7:0.04
    8:0.02
    9:0.10
    10:0.02
    11:0.03
    Negative Logits
     Wednesday
    -2.99
     Tuesday
    -2.95
     Monday
    -2.94
     Thursday
    -2.92
     Saturday
    -2.91
     Friday
    -2.80
     Sunday
    -2.51
    Saturday
    -2.47
    ™:
    -2.43
     tonight
    -2.37
    POSITIVE LOGITS
    '."
    3.80
    .""
    3.80
    )."
    3.64
    )"
    3.53
    ..."
    3.39
    )",
    3.23
    """
    2.94
    ',"
    2.89
    ;"
    2.80
    .",
    2.68
    Activations Density 0.028%

    No Known Activations