© 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. 862
    Prev
    Next
    INDEX
    Explanations

    questions and phrases indicating uncertainty or seeking clarification

    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
    2:0.13
    3:0.36
    4:0.09
    5:0.02
    6:0.03
    7:0.08
    8:0.04
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    ラン
    -1.73
     resumed
    -1.63
     reportedly
    -1.59
     allegedly
    -1.44
    ¶
    -1.36
     omin
    -1.36
     ostensibly
    -1.35
     plummeted
    -1.32
     promptly
    -1.31
     virtually
    -1.31
    POSITIVE LOGITS
     anymore
    2.26
    orget
    2.24
     nor
    2.16
    soType
    1.83
    erker
    1.78
     tho
    1.73
     haha
    1.66
    enne
    1.58
    adena
    1.56
    myra
    1.53
    Activations Density 0.106%

    No Known Activations