© 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. 9376
    Prev
    Next
    INDEX
    Explanations

    references to quantities and categories

    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
    0:0.05
    1:0.02
    2:0.04
    3:0.18
    4:0.06
    5:0.06
    6:0.02
    7:0.08
    8:0.03
    9:0.02
    10:0.36
    11:0.03
    Negative Logits
    imgur
    -2.29
    culosis
    -2.19
    mma
    -2.13
    hello
    -2.10
    ebin
    -2.05
    owler
    -2.01
    geist
    -2.00
    inventoryQuantity
    -2.00
    itsch
    -1.99
    uthor
    -1.98
    POSITIVE LOGITS
     apiece
    3.92
     each
    3.07
     distinct
    2.87
     consecut
    2.79
     pairs
    2.76
     respectively
    2.59
     alternating
    2.44
     chosen
    2.41
     identical
    2.38
     separated
    2.35
    Activations Density 0.241%

    No Known Activations