© 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. 14332
    Prev
    Next
    INDEX
    Explanations

    numerical rankings and competitive standings

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.06
    4:0.05
    5:0.03
    6:0.11
    7:0.09
    8:0.04
    9:0.16
    10:0.02
    11:0.30
    Negative Logits
     renovations
    -2.44
    Relations
    -2.27
     processes
    -2.23
     APIs
    -2.13
     philosophies
    -2.13
     negotiations
    -2.12
    ascript
    -2.06
     procedures
    -2.05
     Suite
    -2.03
    OPS
    -2.02
    POSITIVE LOGITS
     spot
    2.51
    ranked
    2.48
     position
    2.47
     offender
    2.46
     hitter
    2.40
    undai
    2.31
    breaker
    2.31
     bidder
    2.24
     contender
    2.24
    anova
    2.22
    Activations Density 0.006%

    No Known Activations