© 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. 8345
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate problem-solving and data analysis

    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
    2:0.05
    3:0.04
    4:0.37
    5:0.02
    6:0.06
    7:0.10
    8:0.02
    9:0.04
    10:0.03
    11:0.12
    Negative Logits
     sidx
    -2.96
     tradem
    -2.39
    bon
    -2.34
    龍喚士
    -2.31
    ishi
    -2.29
    antry
    -2.22
    soType
    -2.21
     oath
    -2.19
     Mehran
    -2.18
     Masquerade
    -2.18
    POSITIVE LOGITS
    Problem
    6.79
    Solution
    6.49
     problem
    6.49
    problem
    6.49
     solution
    6.29
     Solution
    6.02
     Problem
    6.00
     problems
    5.91
     solutions
    5.66
     solve
    5.59
    Activations Density 0.290%

    No Known Activations