© 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. 9174
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence structures

    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
    0:0.12
    1:0.04
    2:0.03
    3:0.07
    4:0.03
    5:0.04
    6:0.28
    7:0.03
    8:0.04
    9:0.17
    10:0.02
    11:0.07
    Negative Logits
     collapses
    -4.35
     butterflies
    -4.08
     atomic
    -3.95
     Meteor
    -3.94
     Towers
    -3.89
     collapse
    -3.58
     toast
    -3.54
     Kingdom
    -3.53
    KA
    -3.52
     meteor
    -3.46
    POSITIVE LOGITS
     Fil
    8.20
    Fil
    8.07
    fil
    7.99
     fil
    7.06
    FIL
    6.96
     FIL
    6.85
    filename
    6.78
     filename
    6.06
     filament
    4.85
    Franc
    4.80
    Activations Density 0.002%

    No Known Activations