© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 28082
    Prev
    Next
    INDEX
    Explanations

    negations or qualifiers indicating doubt 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
    1:0.02
    2:0.05
    3:0.06
    4:0.06
    5:0.03
    6:0.15
    7:0.40
    8:0.02
    9:0.03
    10:0.04
    11:0.06
    Negative Logits
     orders
    -1.62
     deliveries
    -1.60
    unia
    -1.57
     Orders
    -1.44
    覚醒
    -1.43
    Purchase
    -1.35
    along
    -1.35
     carts
    -1.35
     Blossom
    -1.34
    Lear
    -1.33
    POSITIVE LOGITS
    pose
    1.57
    iour
    1.40
    hed
    1.37
    Picture
    1.36
    imensional
    1.33
     dent
    1.32
     IPM
    1.30
    CVE
    1.30
    polit
    1.29
    olars
    1.28
    Activations Density 0.073%

    No Known Activations