© 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. 10-ATT-KK
    11. 21103
    Prev
    Next
    INDEX
    Explanations

    discussion around memory formation and attention

    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
    0:0.08
    1:0.06
    2:0.05
    3:0.06
    4:0.13
    5:0.03
    6:0.04
    7:0.27
    8:0.02
    9:0.05
    10:0.04
    11:0.11
    Negative Logits
     Homeless
    -2.41
     testimonies
    -2.39
     Jenn
    -2.39
    EF
    -2.37
    \\\\\\\\
    -2.33
    Hol
    -2.32
     Yaz
    -2.32
     mosqu
    -2.29
    \-
    -2.27
    Proof
    -2.24
    POSITIVE LOGITS
    anium
    2.98
     Mechdragon
    2.53
    iets
    2.49
    icut
    2.44
    iferation
    2.31
    ulp
    2.29
    paces
    2.26
    pace
    2.25
     pots
    2.25
    itus
    2.22
    Activations Density 0.001%

    No Known Activations