© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    references to government policies and regulations

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.04
    4:0.07
    5:0.05
    6:0.03
    7:0.05
    8:0.03
    9:0.15
    10:0.02
    11:0.44
    Negative Logits
    etheless
    -2.32
    zilla
    -2.20
    ipel
    -2.02
    rils
    -1.97
     folds
    -1.97
     structures
    -1.91
    olon
    -1.90
    insula
    -1.89
     stacks
    -1.89
     Tracks
    -1.88
    POSITIVE LOGITS
     purposes
    3.70
     reasons
    3.63
     purpose
    3.50
     sake
    2.86
     enjoyment
    2.85
     reason
    2.84
     gratification
    2.64
     Purpose
    2.59
     benefit
    2.36
     demonstration
    2.36
    Activations Density 0.136%

    No Known Activations