© 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. 3-ATT-KK
    11. 13693
    Prev
    Next
    INDEX
    Explanations

    JavaScript code syntax related activations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions related to programming and code management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.05
    3:0.03
    4:0.11
    5:0.35
    6:0.05
    7:0.05
    8:0.04
    9:0.06
    10:0.07
    11:0.04
    Negative Logits
    ModLoader
    -2.06
    emale
    -1.95
     insofar
    -1.76
    adra
    -1.74
    FFFF
    -1.74
    ��極
    -1.71
    CLASSIFIED
    -1.69
    Keefe
    -1.69
    ihar
    -1.69
    IRD
    -1.67
    POSITIVE LOGITS
     sep
    1.87
     fri
    1.76
     listen
    1.72
    pour
    1.62
    rust
    1.61
    Liquid
    1.60
     nod
    1.59
     ripple
    1.59
     pm
    1.59
     strains
    1.58
    Activations Density 0.011%

    No Known Activations