© 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. 3-ATT-KK
    11. 12008
    Prev
    Next
    INDEX
    Explanations

    links to URLs and internet-based text references

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to financial reports and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.06
    2:0.05
    3:0.01
    4:0.05
    5:0.37
    6:0.09
    7:0.05
    8:0.04
    9:0.05
    10:0.09
    11:0.05
    Negative Logits
    idable
    -1.87
     dexter
    -1.82
    dependent
    -1.80
     locom
    -1.79
    igree
    -1.77
     glide
    -1.75
     glue
    -1.72
    iculture
    -1.71
     srfAttach
    -1.70
    ependence
    -1.68
    POSITIVE LOGITS
     journalistic
    2.56
     Reporting
    2.38
     quoting
    2.35
     publishes
    2.34
     publication
    2.34
     podcasts
    2.32
     Editorial
    2.31
    reports
    2.31
     citations
    2.28
     newsletter
    2.27
    Activations Density 0.580%

    No Known Activations