© 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. 19442
    Prev
    Next
    INDEX
    Explanations

    references to academic credentials and achievements, specifically regarding MFA programs and honorary degrees

    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
    0:0.07
    1:0.27
    2:0.05
    3:0.07
    4:0.04
    5:0.02
    6:0.09
    7:0.08
    8:0.04
    9:0.05
    10:0.08
    11:0.09
    Negative Logits
     Plastic
    -2.97
     Slot
    -2.73
    onen
    -2.53
    usha
    -2.53
    Sold
    -2.40
    gel
    -2.39
     Held
    -2.33
    iour
    -2.30
     Bundes
    -2.29
     Sand
    -2.28
    POSITIVE LOGITS
    degree
    5.34
     degree
    5.34
     Degree
    4.91
     degrees
    4.66
     Deg
    3.65
     deg
    3.42
    deg
    3.27
    rees
    2.94
     dism
    2.87
     shades
    2.67
    Activations Density 0.003%

    No Known Activations