© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 11549
    Prev
    Next
    INDEX
    Explanations

    text related to web links and 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
    0:0.11
    1:0.02
    2:0.05
    3:0.18
    4:0.04
    5:0.08
    6:0.08
    7:0.08
    8:0.12
    9:0.02
    10:0.14
    11:0.02
    Negative Logits
     Sloven
    -2.44
    ulic
    -2.16
     coasts
    -2.14
     floats
    -2.11
     Berm
    -2.11
     Bees
    -2.07
     Floating
    -2.01
     pse
    -1.98
     agric
    -1.94
     soils
    -1.92
    POSITIVE LOGITS
    item
    2.37
    EStream
    2.29
     item
    2.16
    affiliated
    2.14
    arger
    2.12
    Catalog
    2.12
     dealer
    2.07
    Keefe
    2.03
    gerald
    2.03
     Coleman
    2.00
    Activations Density 0.001%

    No Known Activations