© 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. 22598
    Prev
    Next
    INDEX
    Explanations

    specific measurements and specifications related to speed and performance in various contexts

    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
    0:0.12
    1:0.07
    2:0.07
    3:0.07
    4:0.09
    5:0.10
    6:0.05
    7:0.07
    8:0.03
    9:0.12
    10:0.05
    11:0.10
    Negative Logits
    ropolitan
    -2.89
     alienated
    -2.81
     microbiome
    -2.69
    ertodd
    -2.61
    izophren
    -2.57
     custod
    -2.55
    ociated
    -2.51
     curated
    -2.50
    andro
    -2.42
     nurturing
    -2.41
    POSITIVE LOGITS
     Spit
    4.54
     speeds
    4.41
     cruising
    3.83
     speed
    3.70
     climbs
    3.67
    Speed
    3.67
     Speed
    3.62
     gust
    3.54
     glide
    3.42
     altitude
    3.35
    Activations Density 0.098%

    No Known Activations