© 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. 5-ATT-KK
    11. 41903
    Prev
    Next
    INDEX
    Explanations

    references to official organizations or entities involved in investigation or law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.25
    3:0.04
    4:0.03
    5:0.01
    6:0.24
    7:0.21
    8:0.03
    9:0.02
    10:0.06
    11:0.03
    Negative Logits
     showc
    -1.58
     folders
    -1.49
    ゴン
    -1.45
    inarily
    -1.42
     wat
    -1.36
    peed
    -1.32
     auctions
    -1.31
     oneself
    -1.30
     undecided
    -1.27
    田
    -1.27
    POSITIVE LOGITS
     Princ
    1.69
     Kingston
    1.44
     Explos
    1.34
     Reconstruction
    1.34
     Northwest
    1.34
     Crunch
    1.32
    agascar
    1.30
     Earthquake
    1.28
     Crime
    1.28
     1906
    1.27
    Activations Density 0.002%

    No Known Activations