© 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. 13659
    Prev
    Next
    INDEX
    Explanations

    references to societal norms or unexpected behaviors

    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
    0:0.17
    1:0.08
    2:0.09
    3:0.06
    4:0.04
    5:0.03
    6:0.09
    7:0.16
    8:0.02
    9:0.05
    10:0.12
    11:0.04
    Negative Logits
    Bang
    -2.80
     Tripoli
    -2.78
     shrimp
    -2.76
     Cambod
    -2.75
     Benghazi
    -2.55
     Ports
    -2.47
     ashore
    -2.45
    grass
    -2.42
     Bangl
    -2.42
    Ser
    -2.41
    POSITIVE LOGITS
     Einstein
    6.32
     Albert
    4.91
     Hawking
    4.02
     relativity
    3.61
    Albert
    3.60
    instein
    3.26
     Kahn
    3.16
     gravitational
    3.12
     Mandela
    2.86
     Centauri
    2.84
    Activations Density 0.008%

    No Known Activations