© 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. 5-ATT-KK
    11. 17828
    Prev
    Next
    INDEX
    Explanations

    elements related to rights, freedoms, and moral responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.17
    4:0.11
    5:0.03
    6:0.04
    7:0.09
    8:0.07
    9:0.06
    10:0.12
    11:0.08
    Negative Logits
    wat
    -1.68
    expected
    -1.42
     puzz
    -1.39
    WARE
    -1.39
    thought
    -1.39
    lain
    -1.37
     conver
    -1.36
    ustom
    -1.34
    lier
    -1.34
    aston
    -1.33
    POSITIVE LOGITS
     freely
    1.84
     lawfully
    1.77
     responsibly
    1.71
     respectfully
    1.71
     voluntarily
    1.62
    soever
    1.62
     anonymously
    1.60
     ______
    1.57
     safely
    1.53
    ardless
    1.52
    Activations Density 0.097%

    No Known Activations