© 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. 9-ATT-KK
    11. 16779
    Prev
    Next
    INDEX
    Explanations

    activities and events associated with progress and output generation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.20
    4:0.02
    5:0.05
    6:0.02
    7:0.08
    8:0.02
    9:0.02
    10:0.37
    11:0.02
    Negative Logits
     centuries
    -2.45
     millennia
    -2.36
    pite
    -2.28
     Psal
    -2.27
     thous
    -2.26
     ancest
    -2.18
     Few
    -2.15
     incompet
    -2.12
     upbringing
    -2.10
     outnumbered
    -2.09
    POSITIVE LOGITS
    });
    3.09
     usable
    2.90
     officially
    2.90
     feasible
    2.81
    iable
    2.77
     commercially
    2.76
     eligible
    2.74
     viable
    2.68
    IBLE
    2.64
     reimb
    2.57
    Activations Density 0.031%

    No Known Activations