© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8529
    Prev
    Next
    INDEX
    Explanations

    key personal experiences and emotions related to mental health and resilience

    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
    0:0.23
    1:0.10
    2:0.08
    3:0.06
    4:0.03
    5:0.02
    6:0.10
    7:0.12
    8:0.02
    9:0.02
    10:0.13
    11:0.04
    Negative Logits
     Ri
    -2.88
     Vulkan
    -2.77
     Tile
    -2.77
     Nid
    -2.75
     Bronze
    -2.74
     bronze
    -2.69
     Dwar
    -2.69
     Overwatch
    -2.69
     Canaan
    -2.68
     Zot
    -2.65
    POSITIVE LOGITS
     Hughes
    9.09
    Hug
    7.62
     Hug
    4.39
     Chavez
    4.02
     Hugo
    3.58
     Essex
    3.47
     Hull
    3.44
     Hubbard
    3.37
     Hutch
    3.31
     Scully
    3.30
    Activations Density 0.004%

    No Known Activations