© 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. 1114
    Prev
    Next
    INDEX
    Explanations

    acronyms and the names of organizations or entities

    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
    2:0.06
    3:0.18
    4:0.05
    5:0.05
    6:0.03
    7:0.05
    8:0.03
    9:0.04
    10:0.35
    11:0.04
    Negative Logits
     dstg
    -2.58
    essim
    -2.27
     forgetting
    -2.24
    acceptable
    -2.21
     worse
    -2.12
     cance
    -2.02
    ignore
    -1.98
    Failure
    -1.98
    better
    -1.96
    cussion
    -1.87
    POSITIVE LOGITS
     originated
    3.50
     began
    3.15
     started
    2.90
     consisted
    2.77
     commenced
    2.75
     derives
    2.75
     consists
    2.67
     Created
    2.63
     originally
    2.63
     Started
    2.59
    Activations Density 0.280%

    No Known Activations