© 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. 19206
    Prev
    Next
    INDEX
    Explanations

    technical specifications of computer hardware and software systems

    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
    0:0.08
    1:0.03
    2:0.03
    3:0.16
    4:0.09
    5:0.08
    6:0.02
    7:0.16
    8:0.08
    9:0.02
    10:0.17
    11:0.05
    Negative Logits
     dictators
    -2.23
     peasants
    -2.20
    erent
    -2.18
    agers
    -2.17
    nown
    -2.14
    ]}
    -2.14
    uebl
    -2.12
    Americans
    -2.10
     begg
    -2.10
     democracies
    -2.08
    POSITIVE LOGITS
     chipset
    2.51
     256
    2.41
     SSD
    2.40
     128
    2.40
     SATA
    2.31
     GeForce
    2.25
     MPEG
    2.23
     OpenGL
    2.21
     onboard
    2.14
     512
    2.13
    Activations Density 0.037%

    No Known Activations