© 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. 19697
    Prev
    Next
    INDEX
    Explanations

    changes in situations or conditions over time

    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
    2:0.03
    3:0.04
    4:0.05
    5:0.35
    6:0.02
    7:0.03
    8:0.01
    9:0.33
    10:0.01
    11:0.04
    Negative Logits
     housed
    -2.86
    ⓘ
    -2.84
     adorned
    -2.66
     wielded
    -2.58
     represented
    -2.45
     veto
    -2.45
     invincible
    -2.31
     resisted
    -2.27
     safegu
    -2.26
     defended
    -2.25
    POSITIVE LOGITS
     lately
    3.50
     since
    2.86
     Changed
    2.79
     Recently
    2.74
    since
    2.71
    Now
    2.63
     Suddenly
    2.58
    Suddenly
    2.54
    Right
    2.53
     Since
    2.52
    Activations Density 0.167%

    No Known Activations