© 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. 9-ATT-KK
    11. 17067
    Prev
    Next
    INDEX
    Explanations

    code comments and structure in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.06
    2:0.05
    3:0.05
    4:0.09
    5:0.05
    6:0.15
    7:0.04
    8:0.10
    9:0.05
    10:0.08
    11:0.19
    Negative Logits
    Rail
    -3.48
    rail
    -3.32
    >"
    -3.10
    Train
    -3.06
     Shard
    -2.98
     Rail
    -2.97
    !]
    -2.96
    owan
    -2.95
     Millennials
    -2.85
     Entity
    -2.77
    POSITIVE LOGITS
     */
    6.20
     /*
    6.12
    /*
    6.11
    */
    5.53
     /**
    4.26
    /**
    3.94
    ********************************
    3.76
     ''
    3.55
     @@
    3.46
     •
    3.46
    Activations Density 0.000%

    No Known Activations