© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    content related to scientific research and medical processes

    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
    0:0.17
    1:0.07
    2:0.06
    3:0.08
    4:0.07
    5:0.03
    6:0.06
    7:0.11
    8:0.03
    9:0.08
    10:0.10
    11:0.08
    Negative Logits
     Spoon
    -3.27
     Django
    -3.22
     Crunch
    -2.99
     Bever
    -2.90
     Ducks
    -2.83
     bite
    -2.83
     dolphins
    -2.83
    bucks
    -2.82
    buck
    -2.80
     Python
    -2.76
    POSITIVE LOGITS
     epit
    3.68
    helial
    3.63
     apopt
    3.34
     scaff
    3.22
     endot
    3.05
    Mesh
    3.04
     cyt
    2.95
    hene
    2.89
     Kushner
    2.83
     Palestin
    2.80
    Activations Density 0.002%

    No Known Activations