© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14283
    Prev
    Next
    INDEX
    Explanations

    references to significant cultural figures or social issues, particularly those relating to identity and censorship

    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
    0:0.04
    1:0.11
    2:0.04
    3:0.39
    4:0.04
    5:0.02
    6:0.05
    7:0.08
    8:0.03
    9:0.04
    10:0.04
    11:0.07
    Negative Logits
     Die
    -2.31
    ynes
    -2.30
    lings
    -2.25
    zos
    -2.15
     starve
    -2.13
    >]
    -2.12
     ­
    -1.97
     scientifically
    -1.95
     aust
    -1.93
    女
    -1.92
    POSITIVE LOGITS
    Past
    7.18
    past
    7.11
     Past
    7.07
     past
    6.83
    present
    4.28
     Present
    4.28
     future
    4.20
    Future
    4.03
     present
    4.00
    future
    3.95
    Activations Density 0.084%

    No Known Activations