© 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. 20728
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical sequences or counts

    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
    0:0.15
    1:0.12
    2:0.10
    3:0.05
    4:0.05
    5:0.05
    6:0.05
    7:0.13
    8:0.04
    9:0.04
    10:0.10
    11:0.08
    Negative Logits
     ALS
    -2.63
     chem
    -2.62
     maple
    -2.46
     cabbage
    -2.42
     duct
    -2.38
     OPEC
    -2.37
     mushrooms
    -2.35
    nikov
    -2.34
    Saudi
    -2.33
     quartz
    -2.28
    POSITIVE LOGITS
     Byte
    5.18
    Byte
    4.62
     byte
    4.55
    byte
    4.15
    Bytes
    4.01
     bytes
    3.73
    bytes
    3.58
     Bit
    2.90
     Ley
    2.89
    ubi
    2.79
    Activations Density 0.000%

    No Known Activations