© 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. 13131
    Prev
    Next
    INDEX
    Explanations

    specific references to a product named "Mother" and related numerical details

    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
    0:0.08
    1:0.25
    2:0.08
    3:0.04
    4:0.06
    5:0.02
    6:0.06
    7:0.08
    8:0.03
    9:0.04
    10:0.14
    11:0.07
    Negative Logits
     Riv
    -2.87
    ファ
    -2.85
     Ald
    -2.78
     retract
    -2.75
    relative
    -2.73
    Ult
    -2.66
     Mak
    -2.65
     Ult
    -2.59
     Torn
    -2.50
    ォ
    -2.50
    POSITIVE LOGITS
     Brain
    5.74
    Brain
    5.24
    brain
    4.55
     brain
    4.29
     brains
    3.50
     Mind
    3.07
     Hardcore
    2.95
     Neck
    2.91
     brow
    2.87
     Mouth
    2.86
    Activations Density 0.001%

    No Known Activations