© 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. 9-ATT-KK
    11. 17139
    Prev
    Next
    INDEX
    Explanations

    financial terms related to contributions and funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.05
    3:0.30
    4:0.05
    5:0.12
    6:0.02
    7:0.08
    8:0.05
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
    classic
    -2.06
    ossibility
    -1.93
    ibe
    -1.75
    xtap
    -1.74
    Attempt
    -1.71
     impossibility
    -1.71
    �
    -1.70
    esque
    -1.68
    latest
    -1.68
     scenario
    -1.68
    POSITIVE LOGITS
     royalties
    2.15
     redistributed
    2.02
     taxp
    2.02
     revenues
    1.98
     funds
    1.94
     graduates
    1.90
     profits
    1.88
     sponsors
    1.87
     coffers
    1.86
     elsewhere
    1.82
    Activations Density 0.173%

    No Known Activations