© 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. 8949
    Prev
    Next
    INDEX
    Explanations

    references to individual pieces or components

    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
    0:0.08
    1:0.09
    2:0.07
    3:0.04
    4:0.05
    5:0.03
    6:0.11
    7:0.18
    8:0.02
    9:0.04
    10:0.04
    11:0.18
    Negative Logits
     Operating
    -2.47
     Lesbian
    -2.06
     Yaz
    -2.01
    Ly
    -1.87
    grounds
    -1.85
     terminal
    -1.84
     STD
    -1.83
    gt
    -1.83
    path
    -1.82
     tremend
    -1.81
    POSITIVE LOGITS
     pieces
    3.87
     piece
    3.55
     Pieces
    3.05
    pieces
    2.97
     Piece
    2.78
     gems
    2.43
     shards
    2.22
    UGC
    2.18
    piece
    2.15
     strands
    2.09
    Activations Density 0.007%

    No Known Activations