© 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. 5-ATT-KK
    11. 41185
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to specific entities or organizations

    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
    0:0.15
    1:0.35
    2:0.02
    3:0.02
    4:0.02
    5:0.18
    6:0.02
    7:0.01
    8:0.06
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
    thumbnails
    -1.72
    ス
    -1.58
    growth
    -1.56
     Thumbnails
    -1.53
    Norm
    -1.51
     riches
    -1.49
    window
    -1.48
    picture
    -1.47
    world
    -1.47
    oms
    -1.45
    POSITIVE LOGITS
    lished
    2.21
     went
    2.12
     drew
    2.10
     tried
    2.07
     tackled
    2.01
     pushed
    1.99
     attempted
    1.99
     touched
    1.95
     concluded
    1.95
    hower
    1.95
    Activations Density 0.197%

    No Known Activations