© 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. 15700
    Prev
    Next
    INDEX
    Explanations

    references to comparisons or contrasts in contexts involving expectations and observed phenomena

    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
    0:0.16
    1:0.06
    2:0.13
    3:0.06
    4:0.03
    5:0.02
    6:0.09
    7:0.14
    8:0.03
    9:0.04
    10:0.15
    11:0.04
    Negative Logits
    án
    -3.03
    ½
    -3.00
     Dwarf
    -2.93
     Malfoy
    -2.93
    Romney
    -2.91
    █
    -2.89
    ör
    -2.88
     Bundy
    -2.88
    renheit
    -2.83
    Pet
    -2.75
    POSITIVE LOGITS
     AJ
    8.64
     CJ
    6.36
     MJ
    4.12
    JC
    4.07
     JJ
    4.05
     AH
    4.02
     PJ
    3.71
     JC
    3.61
     JM
    3.45
     TJ
    3.45
    Activations Density 0.002%

    No Known Activations