© 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. 15460
    Prev
    Next
    INDEX
    Explanations

    references to specific historical or cultural contexts

    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
    1:0.02
    2:0.03
    3:0.31
    4:0.14
    5:0.16
    6:0.03
    7:0.04
    8:0.03
    9:0.07
    10:0.03
    11:0.05
    Negative Logits
    NY
    -2.76
     NSW
    -2.70
     Queensland
    -2.70
    Australian
    -2.57
    VIDEO
    -2.56
    NZ
    -2.54
     NYC
    -2.54
     NZ
    -2.51
    Dutch
    -2.44
     Brisbane
    -2.44
    POSITIVE LOGITS
    "),
    4.87
    ),"
    4.67
    '),
    4.16
    ),
    4.05
    ")
    3.99
    ").
    3.97
     ),
    3.92
    )—
    3.84
    ')
    3.67
    ?),
    3.63
    Activations Density 0.019%

    No Known Activations