© 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. 15247
    Prev
    Next
    INDEX
    Explanations

    elements of formal discourse and punctuation

    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
    0:0.05
    1:0.35
    2:0.05
    3:0.05
    4:0.04
    5:0.05
    6:0.10
    7:0.04
    8:0.02
    9:0.11
    10:0.03
    11:0.05
    Negative Logits
    emis
    -3.04
    ouch
    -2.73
    undrum
    -2.69
    adoes
    -2.63
    aths
    -2.58
    uct
    -2.53
    ð
    -2.53
    icts
    -2.52
    eches
    -2.51
    selves
    -2.43
    POSITIVE LOGITS
     indicated
    4.18
     specified
    4.16
     acknowledged
    3.98
     claimed
    3.88
     stated
    3.88
     suggested
    3.79
     requested
    3.76
     maintained
    3.74
     supported
    3.71
     reported
    3.69
    Activations Density 0.043%

    No Known Activations