© 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. 5-ATT-KK
    11. 29615
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals or spokespersons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.13
    4:0.08
    5:0.05
    6:0.03
    7:0.03
    8:0.19
    9:0.07
    10:0.17
    11:0.11
    Negative Logits
     BEFORE
    -1.39
    chall
    -1.35
     Unique
    -1.33
     Kinder
    -1.32
    !/
    -1.31
     Zion
    -1.30
     Dracula
    -1.29
     Lobby
    -1.29
     crappy
    -1.28
    kefeller
    -1.27
    POSITIVE LOGITS
     understatement
    1.90
    olor
    1.55
     reply
    1.52
     emoji
    1.50
    \-
    1.46
     fixme
    1.43
    onew
    1.43
     blush
    1.41
    usb
    1.37
     aback
    1.36
    Activations Density 0.006%

    No Known Activations