© 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. 15578
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to data analysis methods and practices

    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
    0:0.11
    1:0.04
    2:0.24
    3:0.05
    4:0.09
    5:0.02
    6:0.10
    7:0.10
    8:0.02
    9:0.03
    10:0.04
    11:0.11
    Negative Logits
    UGH
    -3.14
    iard
    -2.63
    pell
    -2.60
    �
    -2.56
    reth
    -2.49
    ubric
    -2.39
    entin
    -2.39
     comed
    -2.37
    dule
    -2.37
    iven
    -2.37
    POSITIVE LOGITS
     Data
    7.15
     datasets
    6.84
     data
    6.55
     dataset
    6.54
     DATA
    6.26
    Data
    6.09
    data
    6.00
    DATA
    5.12
     Dat
    4.97
     dat
    4.72
    Activations Density 0.302%

    No Known Activations