© 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. 10-ATT-KK
    11. 10430
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.22
    3:0.03
    4:0.12
    5:0.30
    6:0.02
    7:0.05
    8:0.04
    9:0.10
    10:0.01
    11:0.02
    Negative Logits
    ?).
    -2.87
    cially
    -2.73
     because
    -2.61
     likewise
    -2.61
     resulted
    -2.53
    cause
    -2.52
    because
    -2.48
    ?]
    -2.47
     interestingly
    -2.46
     nonetheless
    -2.43
    POSITIVE LOGITS
     Posted
    3.02
     •
    2.93
     Random
    2.90
    WASHINGTON
    2.79
     Everywhere
    2.66
    anchester
    2.61
    ORTS
    2.60
    Default
    2.59
     Now
    2.56
    WAYS
    2.52
    Activations Density 0.016%

    No Known Activations