© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 17041
    Prev
    Next
    INDEX
    Explanations

    references to public figures or events within a political context

    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
    2:0.07
    3:0.07
    4:0.40
    5:0.06
    6:0.03
    7:0.04
    8:0.07
    9:0.05
    10:0.05
    11:0.03
    Negative Logits
    "],
    -5.26
    ",
    -4.95
    "},
    -4.70
    !",
    -4.25
    ".[
    -4.23
    "}
    -4.16
    .",
    -4.07
    "]
    -3.92
    "),
    -3.80
    )",
    -3.64
    POSITIVE LOGITS
    icably
    3.37
    ?)
    3.06
     '
    2.79
    Interstitial
    2.67
     '(
    2.50
    …)
    2.49
     amput
    2.42
     inexpl
    2.41
     regress
    2.41
    aito
    2.41
    Activations Density 0.001%

    No Known Activations