© 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. 21330
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes

    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
    0:0.13
    1:0.04
    2:0.07
    3:0.11
    4:0.06
    5:0.18
    6:0.11
    7:0.06
    8:0.04
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
     relocation
    -2.27
     locality
    -2.23
     reconstruction
    -2.04
     hunting
    -2.01
     closures
    -1.98
     semantics
    -1.95
     architecture
    -1.93
     conserv
    -1.91
     sled
    -1.89
     shelters
    -1.89
    POSITIVE LOGITS
    pill
    2.38
    row
    2.30
    vc
    2.28
     Coup
    2.18
    DIV
    2.17
    div
    2.16
    pta
    2.10
    Tea
    2.08
    column
    2.07
    GE
    2.06
    Activations Density 0.020%

    No Known Activations