© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 7717
    Prev
    Next
    INDEX
    Explanations

    phrases related to the user experience and functionality of technology products

    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
    0:0.02
    1:0.01
    2:0.16
    3:0.15
    4:0.23
    5:0.15
    6:0.01
    7:0.04
    8:0.03
    9:0.10
    10:0.02
    11:0.02
    Negative Logits
     ­
    -2.25
    BuyableInstoreAndOnline
    -2.05
    )]
    -2.00
     )]
    -1.98
    TPPStreamerBot
    -1.97
    ­
    -1.93
    "},"
    -1.91
    "))
    -1.88
    >]
    -1.86
     Mississ
    -1.83
    POSITIVE LOGITS
    !.
    4.16
    .""
    3.81
     :-)
    3.69
    !".
    3.65
     :)
    3.62
    .(
    3.59
     ().
    3.48
     ;)
    3.43
    .....
    3.41
    ....
    3.38
    Activations Density 1.881%

    No Known Activations