© 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. 5116
    Prev
    Next
    INDEX
    Explanations

    elements related to user-friendly product features and ease of use

    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
    0:0.10
    1:0.02
    2:0.06
    3:0.26
    4:0.03
    5:0.08
    6:0.01
    7:0.08
    8:0.03
    9:0.02
    10:0.24
    11:0.01
    Negative Logits
     resurg
    -2.24
     Confeder
    -2.10
     Marketable
    -2.02
     animosity
    -2.01
    BuyableInstoreAndOnline
    -1.98
     tainted
    -1.93
     feud
    -1.93
     estranged
    -1.90
     reneg
    -1.89
     controversies
    -1.87
    POSITIVE LOGITS
     simple
    2.97
    simple
    2.91
     easy
    2.75
     basics
    2.68
     Simple
    2.68
     tutorial
    2.66
     Easy
    2.65
     simplest
    2.65
    Setup
    2.59
    Simple
    2.57
    Activations Density 0.280%

    No Known Activations