© 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. 43451
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and data transfer

    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
    1:0.03
    2:0.07
    3:0.07
    4:0.26
    5:0.03
    6:0.14
    7:0.11
    8:0.04
    9:0.03
    10:0.08
    11:0.08
    Negative Logits
     favorably
    -1.46
    ignty
    -1.44
    eared
    -1.40
    anooga
    -1.35
    hematically
    -1.34
     affected
    -1.32
    aez
    -1.32
    ificantly
    -1.29
     suicidal
    -1.28
    ounces
    -1.27
    POSITIVE LOGITS
     Radar
    1.77
    interstitial
    1.62
    Plex
    1.40
     Wiz
    1.40
     Showdown
    1.33
     aisle
    1.31
    taboola
    1.29
    AV
    1.28
    pic
    1.28
    wik
    1.27
    Activations Density 0.028%

    No Known Activations