© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 21038
    Prev
    Next
    INDEX
    Explanations

    references to measurements of area and distance

    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
    0:0.10
    1:0.04
    2:0.16
    3:0.12
    4:0.03
    5:0.14
    6:0.06
    7:0.10
    8:0.04
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     Genius
    -2.28
     sooner
    -2.23
     forgiving
    -2.19
     bracelet
    -2.16
     kid
    -2.15
     kids
    -2.11
     Brees
    -2.11
    ilant
    -2.10
    ebted
    -2.09
     salute
    -2.08
    POSITIVE LOGITS
    Area
    2.50
    sect
    2.44
     coh
    2.42
    ommod
    2.41
     annex
    2.35
     mosqu
    2.31
    phis
    2.29
    rawdownloadcloneembedreportprint
    2.27
     XY
    2.24
     vectors
    2.23
    Activations Density 0.000%

    No Known Activations