© 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. 3-ATT-KK
    11. 8210
    Prev
    Next
    INDEX
    Explanations

    general observations or statements regarding societal and scientific issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.13
    2:0.10
    3:0.05
    4:0.08
    5:0.08
    6:0.09
    7:0.06
    8:0.10
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
    itaire
    -1.49
    terness
    -1.44
    ikers
    -1.36
    etheless
    -1.35
    iannopoulos
    -1.33
    mosp
    -1.31
    gars
    -1.30
    gom
    -1.30
    onymous
    -1.25
    eller
    -1.24
    POSITIVE LOGITS
     slept
    1.28
     sleeps
    1.27
     borrow
    1.17
     nap
    1.15
     Sic
    1.15
     Dia
    1.14
     Agric
    1.13
     NAV
    1.09
     TOD
    1.09
     max
    1.09
    Activations Density 0.365%

    No Known Activations