© 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. 8719
    Prev
    Next
    INDEX
    Explanations

    content related to questioning or uncertainty

    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
    1:0.03
    2:0.07
    3:0.05
    4:0.14
    5:0.02
    6:0.42
    7:0.07
    8:0.02
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
    doms
    -1.38
    iasco
    -1.37
    vous
    -1.26
    algia
    -1.17
    iatrics
    -1.17
     spores
    -1.16
    rency
    -1.15
    anche
    -1.15
     remembers
    -1.14
    rimination
    -1.13
    POSITIVE LOGITS
     behest
    1.60
     level
    1.56
     outset
    1.55
     expense
    1.50
    EStream
    1.47
     disposal
    1.40
     ripe
    1.38
     end
    1.34
    mast
    1.30
     intervals
    1.30
    Activations Density 0.210%

    No Known Activations