© 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. 14022
    Prev
    Next
    INDEX
    Explanations

    specific individuals and locations related to political or social events

    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
    0:0.05
    1:0.02
    2:0.15
    3:0.09
    4:0.22
    5:0.14
    6:0.03
    7:0.07
    8:0.03
    9:0.08
    10:0.03
    11:0.04
    Negative Logits
    ]),
    -3.48
    )),
    -3.16
    ,[
    -3.11
    ])
    -2.80
    theless
    -2.75
    []
    -2.71
     [|
    -2.70
    $,
    -2.69
    !),
    -2.65
    "],
    -2.65
    POSITIVE LOGITS
     Photograph
    5.05
     …"
    3.42
     …
    3.17
     '.
    3.08
     Illust
    3.06
     Nasa
    2.90
    …"
    2.86
     Facebook
    2.69
     WhatsApp
    2.64
     �
    2.63
    Activations Density 0.003%

    No Known Activations