© 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. 15846
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that indicate size, complexity, and other qualitative assessments

    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
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.31
    6:0.02
    7:0.03
    8:0.02
    9:0.30
    10:0.02
    11:0.04
    Negative Logits
    aires
    -2.36
     livest
    -2.29
     resumes
    -2.12
    hner
    -2.09
     ACTIONS
    -2.07
    kel
    -2.04
     cease
    -2.03
     proceeds
    -2.00
     commence
    -2.00
     Known
    -1.99
    POSITIVE LOGITS
     too
    3.01
    too
    2.65
     awfully
    2.60
     badly
    2.46
    UTF
    2.37
     Too
    2.33
    orry
    2.31
    erous
    2.30
    stretched
    2.29
    imental
    2.25
    Activations Density 0.038%

    No Known Activations