© 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. 15019
    Prev
    Next
    INDEX
    Explanations

    content related to digital marketing and website optimization

    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
    0:0.09
    1:0.05
    2:0.09
    3:0.05
    4:0.03
    5:0.03
    6:0.27
    7:0.03
    8:0.02
    9:0.22
    10:0.03
    11:0.02
    Negative Logits
     Seah
    -3.69
    ascade
    -3.65
     Sheila
    -3.63
     Shah
    -3.60
     Herald
    -3.55
     SEA
    -3.48
    outheast
    -3.36
     Shepherd
    -3.35
    antle
    -3.35
    izon
    -3.31
    POSITIVE LOGITS
     Fun
    8.57
    Fun
    7.89
    fun
    7.51
     FUN
    6.58
     fun
    6.09
    FUN
    5.52
     Funk
    4.37
     amusement
    4.33
     pleasure
    3.99
     Comedy
    3.94
    Activations Density 0.007%

    No Known Activations