© 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. 9576
    Prev
    Next
    INDEX
    Explanations

    segments featuring the symbol "Ċ."

    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
    0:0.14
    1:0.07
    2:0.11
    3:0.06
    4:0.03
    5:0.02
    6:0.21
    7:0.10
    8:0.02
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
    staff
    -2.82
     Scully
    -2.68
     Coyotes
    -2.61
    cycles
    -2.53
    boss
    -2.49
    rity
    -2.47
    ogy
    -2.47
    Yang
    -2.46
    arge
    -2.45
     calf
    -2.43
    POSITIVE LOGITS
     Benjamin
    8.26
    jamin
    5.00
    Ben
    4.38
     Franklin
    3.49
     Judah
    3.39
     Netanyahu
    3.32
     Ben
    3.32
     BEN
    3.30
     Bernard
    3.18
    ben
    3.00
    Activations Density 0.002%

    No Known Activations