© 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. 16261
    Prev
    Next
    INDEX
    Explanations

    specific details related to incidents, conditions, or setups involving victims and injuries

    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
    3:0.04
    4:0.06
    5:0.12
    6:0.02
    7:0.02
    8:0.01
    9:0.55
    10:0.01
    11:0.05
    Negative Logits
    NetMessage
    -2.49
    asta
    -2.20
    aug
    -2.18
    laun
    -2.02
    conduct
    -2.01
    Duration
    -1.94
    ennial
    -1.93
    uclear
    -1.92
    ogo
    -1.91
    mast
    -1.89
    POSITIVE LOGITS
     varies
    3.82
     discrepancy
    3.53
     discrepancies
    3.39
     differs
    3.31
     depends
    3.26
     mismatch
    3.23
     differential
    3.22
     adjustments
    3.11
     dictated
    3.10
     vary
    3.09
    Activations Density 1.125%

    No Known Activations