© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21242
    Prev
    Next
    INDEX
    Explanations

    compound phrases and various conjunctions

    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
    0:0.04
    1:0.03
    2:0.04
    3:0.05
    4:0.27
    5:0.02
    6:0.07
    7:0.28
    8:0.01
    9:0.03
    10:0.03
    11:0.07
    Negative Logits
     Law
    -3.62
     LAW
    -3.25
     Laws
    -3.23
     Lawyers
    -2.92
    Law
    -2.82
    law
    -2.73
     Legal
    -2.68
    Lic
    -2.58
    ه
    -2.54
     Ter
    -2.52
    POSITIVE LOGITS
    ospels
    3.06
    ppo
    2.85
    ���
    2.78
    gemony
    2.71
    endas
    2.68
     Chomsky
    2.46
    bishop
    2.44
    opolis
    2.39
    yg
    2.38
    hner
    2.36
    Activations Density 0.023%

    No Known Activations