© 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 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. 20836
    Prev
    Next
    INDEX
    Explanations

    references to media and cultural events related to fair use and artistic expression

    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
    1:0.37
    2:0.04
    3:0.03
    4:0.05
    5:0.02
    6:0.14
    7:0.08
    8:0.02
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
    alone
    -3.25
    rieg
    -2.72
    itialized
    -2.68
     garg
    -2.67
    oneliness
    -2.56
    rology
    -2.56
    iatus
    -2.56
    Interstitial
    -2.51
    lesi
    -2.50
    sten
    -2.49
    POSITIVE LOGITS
     Fair
    8.93
    Fair
    8.56
     fair
    8.23
    fair
    7.25
     faire
    5.09
     fairness
    4.84
     unfair
    4.52
     equitable
    4.03
     reasonable
    3.61
     Equal
    3.40
    Activations Density 0.038%

    No Known Activations