© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    references to problem-solving and complex challenges

    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
    1:0.03
    2:0.03
    3:0.03
    4:0.13
    5:0.02
    6:0.03
    7:0.11
    8:0.01
    9:0.04
    10:0.02
    11:0.45
    Negative Logits
     broadcaster
    -2.25
     TMZ
    -2.22
     breaths
    -2.22
     strides
    -2.06
     endors
    -2.02
    ochet
    -1.97
     filmmaker
    -1.96
     airing
    -1.96
     channel
    -1.95
     stance
    -1.93
    POSITIVE LOGITS
     puzzles
    4.07
     puzzle
    3.56
     solved
    3.48
     Puzzles
    3.45
     mysteries
    3.23
     equations
    3.21
     problems
    3.19
    problem
    3.12
     Problems
    3.11
     trivia
    2.99
    Activations Density 0.058%

    No Known Activations