© 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. 553
    Prev
    Next
    INDEX
    Explanations

    symbols or characters indicative of formatting or coding artifacts

    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
    0:0.10
    1:0.03
    2:0.08
    3:0.03
    4:0.04
    5:0.03
    6:0.26
    7:0.04
    8:0.09
    9:0.19
    10:0.03
    11:0.02
    Negative Logits
     Clarke
    -4.19
     Coil
    -4.05
    catentry
    -4.02
    Alice
    -3.97
     Ö
    -3.86
    Alabama
    -3.84
    alin
    -3.80
     Lawson
    -3.74
     Palin
    -3.66
    Machine
    -3.65
    POSITIVE LOGITS
     Gent
    10.89
     gent
    7.55
    gent
    5.51
     Vincent
    4.04
     Gast
    3.98
     nob
    3.97
     Sag
    3.87
     Pant
    3.86
     ghetto
    3.80
     Torah
    3.76
    Activations Density 0.000%

    No Known Activations