© 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. 15733
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal struggle and transformation

    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
    1:0.06
    2:0.11
    3:0.03
    4:0.02
    5:0.02
    6:0.12
    7:0.13
    8:0.01
    9:0.04
    10:0.11
    11:0.07
    Negative Logits
    CU
    -3.29
     Kasich
    -3.20
     Paragu
    -3.01
    Flo
    -2.95
     CU
    -2.77
    Tokens
    -2.68
    Ky
    -2.60
     Buc
    -2.54
     Umb
    -2.54
     GNOME
    -2.47
    POSITIVE LOGITS
     Smith
    8.61
    Smith
    8.19
    smith
    5.01
    mith
    3.91
     Mormonism
    3.69
     Nau
    3.46
     Tanner
    3.43
     Prophet
    3.37
     Gibbs
    3.26
     Mormon
    3.20
    Activations Density 0.051%

    No Known Activations