© 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. 231
    Prev
    Next
    INDEX
    Explanations

    references to research findings and statistical analysis

    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
    1:0.02
    2:0.04
    3:0.14
    4:0.02
    5:0.06
    6:0.01
    7:0.04
    8:0.02
    9:0.02
    10:0.53
    11:0.02
    Negative Logits
    oller
    -1.79
     attRot
    -1.77
    $.
    -1.72
     transpired
    -1.68
     Became
    -1.67
    iasm
    -1.66
     Suppose
    -1.65
    edition
    -1.63
    Writer
    -1.58
    IDER
    -1.55
    POSITIVE LOGITS
     differently
    3.21
     faster
    3.18
     twice
    3.13
     sparing
    3.03
     separately
    3.02
     concurrently
    3.01
     continuously
    2.92
     quicker
    2.90
     inconsist
    2.90
     simultaneously
    2.88
    Activations Density 1.741%

    No Known Activations