© 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. 10123
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and legal institutions

    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
    1:0.02
    2:0.02
    3:0.03
    4:0.07
    5:0.10
    6:0.05
    7:0.04
    8:0.02
    9:0.51
    10:0.02
    11:0.06
    Negative Logits
    avorite
    -2.49
    aneous
    -2.44
    nian
    -2.42
    ibaba
    -2.31
    EEK
    -2.31
    tainment
    -2.28
    OME
    -2.23
    upiter
    -2.21
    �
    -2.20
    hiba
    -2.18
    POSITIVE LOGITS
     Its
    4.98
    Its
    4.90
     its
    4.74
     ITS
    3.81
     recommends
    3.55
     regulates
    3.54
     conducts
    3.52
     itself
    3.52
     intends
    3.44
     considers
    3.43
    Activations Density 1.779%

    No Known Activations