© 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. 10-ATT-KK
    6. 14142
    Prev
    Next
    INDEX
    Explanations

    connections between walking and social or community activities

    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
    0:0.04
    1:0.05
    2:0.04
    3:0.03
    4:0.11
    5:0.03
    6:0.04
    7:0.40
    8:0.02
    9:0.04
    10:0.04
    11:0.12
    Negative Logits
     Poo
    -2.63
     toes
    -2.43
     Rut
    -2.31
     Ame
    -2.28
     Jesse
    -2.27
     Rowe
    -2.24
    reed
    -2.23
     Rivers
    -2.22
     Wander
    -2.22
     toe
    -2.21
    POSITIVE LOGITS
    adobe
    2.67
    alin
    2.60
    ATIONAL
    2.54
    龍
    2.48
    /​
    2.40
    fman
    2.38
    ador
    2.30
    Avg
    2.27
    atom
    2.26
    』
    2.26
    Activations Density 0.021%

    No Known Activations