© 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. 13681
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with rankings or selections in drafts

    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
    0:0.06
    1:0.05
    2:0.05
    3:0.08
    4:0.08
    5:0.04
    6:0.26
    7:0.07
    8:0.03
    9:0.11
    10:0.04
    11:0.07
    Negative Logits
     opponent
    -3.31
     opponents
    -3.25
     opposition
    -3.21
     NCAA
    -3.16
     Auditor
    -3.15
     stadiums
    -3.04
    Opp
    -2.97
     campuses
    -2.95
     opposing
    -2.90
     Stadium
    -2.86
    POSITIVE LOGITS
    obyl
    3.62
    覚醒
    3.37
    treatment
    2.93
    dial
    2.87
    entry
    2.75
    Dial
    2.73
    Dialogue
    2.67
    Alias
    2.66
     Entry
    2.63
    Loc
    2.61
    Activations Density 0.003%

    No Known Activations