© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    variations of words and phrases related to actions or descriptors in text, specifically in a coded or structured format

    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
    0:0.04
    1:0.03
    2:0.06
    3:0.09
    4:0.09
    5:0.28
    6:0.03
    7:0.07
    8:0.03
    9:0.11
    10:0.06
    11:0.05
    Negative Logits
     legitimately
    -2.81
     increasingly
    -2.55
     realistically
    -2.53
     adequately
    -2.49
     seriously
    -2.48
     consistently
    -2.47
     genuinely
    -2.46
     appropriately
    -2.45
     understandably
    -2.45
     extensively
    -2.44
    POSITIVE LOGITS
     ⓘ
    3.04
     <-
    2.90
     Ago
    2.75
     Adds
    2.63
    "},"
    2.59
     ):
    2.59
    ":
    2.57
    "}
    2.56
     =
    2.47
     Vs
    2.47
    Activations Density 0.652%

    No Known Activations