© 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. 5-ATT-KK
    11. 7896
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.00
    2:0.07
    3:0.04
    4:0.09
    5:0.02
    6:0.02
    7:0.40
    8:0.03
    9:0.02
    10:0.16
    11:0.08
    Negative Logits
     perk
    -1.54
     voic
    -1.51
    iences
    -1.48
    BILITIES
    -1.47
     airst
    -1.43
    gencies
    -1.41
     grate
    -1.40
     Roof
    -1.40
     mell
    -1.40
     airs
    -1.39
    POSITIVE LOGITS
     papers
    2.00
    papers
    1.91
    pdf
    1.86
     Proceedings
    1.80
    Merit
    1.79
     paper
    1.61
    study
    1.60
     proofs
    1.58
     Transactions
    1.55
    PDF
    1.55
    Activations Density 0.008%

    No Known Activations