© 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. 43337
    Prev
    Next
    INDEX
    Explanations

    references to teams and their performance in competitive contexts

    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
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.03
    7:0.04
    8:0.02
    9:0.05
    10:0.47
    11:0.12
    Negative Logits
     Attribution
    -1.84
     DMCA
    -1.64
     Devices
    -1.63
     shutter
    -1.56
     TED
    -1.54
     Photoshop
    -1.53
     eas
    -1.52
     Leica
    -1.51
    enegger
    -1.51
    idian
    -1.51
    POSITIVE LOGITS
    eki
    1.85
    rongh
    1.79
     lineup
    1.72
    arsity
    1.67
     nucleus
    1.66
     roster
    1.65
    HOME
    1.60
    elta
    1.59
    nil
    1.57
    TRY
    1.57
    Activations Density 0.335%

    No Known Activations