© 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. 9898
    Prev
    Next
    INDEX
    Explanations

    instances of statistical and structural analysis in the context of publications and media representation

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.05
    4:0.16
    5:0.04
    6:0.04
    7:0.20
    8:0.02
    9:0.10
    10:0.03
    11:0.23
    Negative Logits
     unlucky
    -2.42
    abiding
    -2.39
     thief
    -2.35
     liar
    -2.28
    Added
    -2.17
    terness
    -2.14
    effect
    -2.13
     attacker
    -2.08
    ctuary
    -2.07
    erate
    -2.06
    POSITIVE LOGITS
     newsletters
    3.50
     lectures
    3.36
     interviews
    3.33
     presentations
    3.29
     guides
    3.29
     videos
    3.17
     sketches
    3.16
     tutorials
    3.12
     seminars
    3.07
     essays
    3.07
    Activations Density 0.137%

    No Known Activations