© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 4361
    Prev
    Next
    INDEX
    Explanations

    references to rewards or metrics in a performance context

    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
    0:0.03
    1:0.47
    2:0.03
    3:0.05
    4:0.03
    5:0.03
    6:0.03
    7:0.05
    8:0.02
    9:0.05
    10:0.09
    11:0.07
    Negative Logits
     1905
    -2.61
     irresistible
    -2.55
    天
    -2.55
     1906
    -2.45
     1904
    -2.44
    universal
    -2.44
    905
    -2.42
    026
    -2.33
    Usually
    -2.31
    pheus
    -2.24
    POSITIVE LOGITS
     while
    6.48
     whilst
    6.42
    while
    6.17
     While
    3.97
    While
    3.88
     Whilst
    3.64
    anwhile
    3.49
     whereas
    3.36
     Meanwhile
    3.27
     awhile
    2.69
    Activations Density 0.046%

    No Known Activations