© 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. 9-ATT-KK
    11. 12810
    Prev
    Next
    INDEX
    Explanations

    dates and time references

    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
    0:0.02
    1:0.41
    2:0.03
    3:0.10
    4:0.03
    5:0.13
    6:0.02
    7:0.07
    8:0.04
    9:0.03
    10:0.02
    11:0.05
    Negative Logits
     unparalleled
    -2.52
    onga
    -2.33
     Packs
    -2.32
     sizeable
    -2.30
     PACK
    -2.27
     Firstly
    -2.21
     phenomenal
    -2.19
     lapt
    -2.18
    oubted
    -2.17
     immense
    -2.15
    POSITIVE LOGITS
    same
    2.73
    iary
    2.62
    emis
    2.46
    vre
    2.45
    alia
    2.40
    Catalog
    2.39
    sylv
    2.39
    Nor
    2.37
    Sept
    2.37
     Revised
    2.35
    Activations Density 0.019%

    No Known Activations