© 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. 27915
    Prev
    Next
    INDEX
    Explanations

    phrases related to valuable or significant collections of information, particularly leaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.02
    2:0.07
    3:0.04
    4:0.09
    5:0.03
    6:0.04
    7:0.32
    8:0.04
    9:0.04
    10:0.14
    11:0.08
    Negative Logits
    SPA
    -1.66
    MODE
    -1.56
     commute
    -1.55
     tilt
    -1.50
     pronounced
    -1.49
     cancel
    -1.48
     curfew
    -1.46
     disappro
    -1.44
     superv
    -1.44
     harmon
    -1.41
    POSITIVE LOGITS
     trove
    2.64
     archives
    2.17
     caches
    2.08
     cache
    2.04
    geries
    1.92
     unearthed
    1.90
     treasure
    1.86
     riches
    1.86
     documents
    1.83
    abilia
    1.83
    Activations Density 0.001%

    No Known Activations