© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 19191
    Prev
    Next
    INDEX
    Explanations

    elements related to puzzles and problem-solving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.02
    2:0.21
    3:0.07
    4:0.03
    5:0.09
    6:0.05
    7:0.06
    8:0.09
    9:0.05
    10:0.03
    11:0.04
    Negative Logits
    assetsadobe
    -3.23
     contrace
    -3.05
    indal
    -2.91
     spons
    -2.89
     Bannon
    -2.76
    ofi
    -2.75
     breastfeeding
    -2.73
    )=(
    -2.70
     FSA
    -2.59
     Houth
    -2.57
    POSITIVE LOGITS
     puzzles
    6.01
     puzzle
    5.90
     solved
    5.38
     solving
    4.86
     solve
    4.65
     Puzzles
    4.60
     Puzzle
    4.28
     puzz
    4.28
     unsolved
    4.23
     maze
    4.14
    Activations Density 0.070%

    No Known Activations