© 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. 10303
    Prev
    Next
    INDEX
    Explanations

    phrases related to software solutions and their effectiveness

    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
    0:0.05
    1:0.08
    2:0.05
    3:0.03
    4:0.15
    5:0.01
    6:0.11
    7:0.25
    8:0.02
    9:0.02
    10:0.04
    11:0.12
    Negative Logits
     voy
    -2.24
     Bound
    -2.07
     checkpoints
    -1.95
     reven
    -1.93
    viron
    -1.87
    wx
    -1.86
     outing
    -1.85
     outings
    -1.83
     Secrets
    -1.83
     Expedition
    -1.82
    POSITIVE LOGITS
     solution
    3.55
     solutions
    3.21
    Solution
    3.20
     Solution
    2.84
    sburg
    2.60
     solved
    2.46
     solve
    2.43
     solving
    2.32
    acea
    2.31
    phal
    2.25
    Activations Density 0.022%

    No Known Activations