© 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. 16885
    Prev
    Next
    INDEX
    Explanations

    punctuations and connectors in sentences

    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
    0:0.15
    1:0.09
    2:0.08
    3:0.08
    4:0.06
    5:0.03
    6:0.09
    7:0.12
    8:0.03
    9:0.04
    10:0.11
    11:0.06
    Negative Logits
     Bac
    -2.09
     Ac
    -2.02
     Dra
    -2.00
     Hydra
    -1.97
     Mal
    -1.95
     Hau
    -1.95
     Ultra
    -1.91
     crystal
    -1.89
     Electro
    -1.87
     Iris
    -1.85
    POSITIVE LOGITS
    uckland
    2.91
    paio
    2.84
    �
    2.77
    foundland
    2.75
    anyahu
    2.72
    DeliveryDate
    2.63
    olkien
    2.61
    ÃÂ
    2.60
    StreamerBot
    2.59
    Gaza
    2.58
    Activations Density 0.003%

    No Known Activations