© 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. 19188
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and their achievements or attributes, particularly in the context of sports or historical events

    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
    0:0.04
    1:0.41
    2:0.03
    3:0.05
    4:0.05
    5:0.04
    6:0.07
    7:0.05
    8:0.04
    9:0.08
    10:0.04
    11:0.07
    Negative Logits
     Grimm
    -2.71
     Rasm
    -2.54
    IRT
    -2.48
     Benghazi
    -2.43
    aimon
    -2.41
    GROUND
    -2.40
     Alm
    -2.39
    atsuki
    -2.37
    irs
    -2.34
     unseen
    -2.34
    POSITIVE LOGITS
     48
    4.99
     47
    4.52
    48
    4.36
     49
    4.28
    47
    4.00
     46
    3.96
    49
    3.94
    46
    3.62
     51
    3.41
     52
    3.40
    Activations Density 0.007%

    No Known Activations