© 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. 20387
    Prev
    Next
    INDEX
    Explanations

    quotes and references that convey intentions or plans regarding truth and corrective actions

    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
    0:0.15
    1:0.08
    2:0.07
    3:0.03
    4:0.03
    5:0.02
    6:0.24
    7:0.09
    8:0.02
    9:0.04
    10:0.15
    11:0.04
    Negative Logits
     creditor
    -3.25
    oros
    -3.04
     guiActiveUn
    -2.96
    Yan
    -2.92
    URI
    -2.82
    neys
    -2.71
     Eur
    -2.68
    ilion
    -2.67
    onial
    -2.61
    roma
    -2.58
    POSITIVE LOGITS
    Chuck
    8.83
     Chuck
    8.47
     chuck
    4.05
     Chop
    3.44
     Grassley
    3.43
     Chap
    3.39
     Huff
    3.37
     Colts
    3.36
     Schumer
    3.30
     CT
    3.29
    Activations Density 0.002%

    No Known Activations