© 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. 21214
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with significant historical events and figures

    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
    0:0.04
    1:0.03
    2:0.02
    3:0.06
    4:0.04
    5:0.05
    6:0.03
    7:0.04
    8:0.02
    9:0.26
    10:0.03
    11:0.33
    Negative Logits
    seless
    -2.17
    oooooooo
    -2.04
    cha
    -2.03
    contained
    -2.01
    ****************
    -1.97
     situated
    -1.95
     quart
    -1.93
    external
    -1.87
    itaire
    -1.86
    ICLE
    -1.86
    POSITIVE LOGITS
     adop
    2.62
     refinement
    2.61
     iterations
    2.55
     prototypes
    2.46
     revisions
    2.43
     previews
    2.40
    prints
    2.39
     stages
    2.36
     advancements
    2.28
     prototyp
    2.27
    Activations Density 0.022%

    No Known Activations