© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28967
    Prev
    Next
    INDEX
    Explanations

    words associated with the concept of obscuring or hiding truth

    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
    2:0.04
    3:0.06
    4:0.15
    5:0.03
    6:0.04
    7:0.38
    8:0.03
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
    ーク
    -1.56
    verty
    -1.53
    gins
    -1.53
    emouth
    -1.49
    eligible
    -1.47
    hement
    -1.46
    =-=-=-=-=-=-=-=-
    -1.44
    Reward
    -1.43
    apest
    -1.43
    ASED
    -1.39
    POSITIVE LOGITS
     altogether
    1.58
    ipedia
    1.44
    kered
    1.42
     proceedings
    1.42
     entrance
    1.42
     entrances
    1.39
     webpage
    1.36
     Hague
    1.33
     anymore
    1.33
    HTML
    1.31
    Activations Density 0.001%

    No Known Activations