© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 7247
    Prev
    Next
    INDEX
    Explanations

    variations of the word "change" along with related concepts of transformation and modification

    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
    0:0.03
    1:0.03
    2:0.02
    3:0.05
    4:0.06
    5:0.05
    6:0.03
    7:0.05
    8:0.02
    9:0.13
    10:0.02
    11:0.47
    Negative Logits
    urdue
    -2.34
     Leban
    -2.13
    ctuary
    -2.08
    ymph
    -2.03
    icum
    -2.02
    interstitial
    -2.02
    unic
    -2.00
     Libraries
    -1.98
    aughter
    -1.94
    glomer
    -1.94
    POSITIVE LOGITS
     demographics
    3.58
     attitudes
    3.15
     lineup
    3.04
     mindset
    3.03
     parameters
    3.01
     trajectory
    3.00
     habits
    2.96
     colors
    2.92
     colours
    2.91
     direction
    2.90
    Activations Density 0.204%

    No Known Activations