© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15135
    Prev
    Next
    INDEX
    Explanations

    phrases related to processing and quality assurance in production

    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
    0:0.11
    1:0.07
    2:0.05
    3:0.07
    4:0.06
    5:0.04
    6:0.16
    7:0.13
    8:0.05
    9:0.04
    10:0.08
    11:0.09
    Negative Logits
     Greenwich
    -2.88
    bledon
    -2.78
     tennis
    -2.61
     Monk
    -2.61
     Tennis
    -2.59
     defensively
    -2.56
    ghai
    -2.44
     Stamford
    -2.41
     Omaha
    -2.40
    orgetown
    -2.34
    POSITIVE LOGITS
     Processing
    5.22
     processing
    5.20
    processing
    4.80
    Process
    4.44
     processed
    4.18
    process
    3.61
     processors
    3.40
     Processor
    3.33
     Process
    3.12
     processor
    3.11
    Activations Density 0.014%

    No Known Activations