© 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. 22834
    Prev
    Next
    INDEX
    Explanations

    phrases related to program management and accountability

    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
    0:0.07
    1:0.27
    2:0.07
    3:0.04
    4:0.05
    5:0.02
    6:0.09
    7:0.13
    8:0.02
    9:0.03
    10:0.11
    11:0.06
    Negative Logits
    pop
    -2.51
    CENT
    -2.49
    oche
    -2.43
    ropy
    -2.35
    lip
    -2.33
     centered
    -2.32
     folds
    -2.28
     Faces
    -2.25
     airs
    -2.25
    lins
    -2.25
    POSITIVE LOGITS
     Technical
    5.00
    Technical
    4.45
     technical
    4.30
    technical
    4.17
     Techn
    2.98
     TECH
    2.81
     Tech
    2.74
     Graphic
    2.64
     Engineering
    2.60
     Hilbert
    2.47
    Activations Density 0.003%

    No Known Activations