© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13612
    Prev
    Next
    INDEX
    Explanations

    technical terms related to structural engineering failures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.05
    3:0.09
    4:0.04
    5:0.06
    6:0.03
    7:0.04
    8:0.37
    9:0.09
    10:0.06
    11:0.03
    Negative Logits
     coward
    -1.27
    stab
    -1.17
    steps
    -1.16
    writers
    -1.15
    write
    -1.12
     thief
    -1.12
     forks
    -1.09
    wrote
    -1.09
     treason
    -1.07
    byter
    -1.06
    POSITIVE LOGITS
    ategy
    1.35
    ptoms
    1.32
     capability
    1.30
    urgy
    1.27
    oming
    1.27
    aceutical
    1.23
    atro
    1.22
     Habit
    1.22
    ubric
    1.21
     roadmap
    1.20
    Activations Density 0.074%

    No Known Activations