© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10418
    Prev
    Next
    INDEX
    Explanations

    occurrences of the comma 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
    0:0.08
    1:0.07
    2:0.09
    3:0.09
    4:0.08
    5:0.09
    6:0.06
    7:0.07
    8:0.08
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     bullies
    -2.58
    enh
    -2.52
     jealous
    -2.50
    Weak
    -2.44
     rocky
    -2.41
     cock
    -2.31
     pil
    -2.29
    hunt
    -2.24
     ruth
    -2.22
     hunts
    -2.22
    POSITIVE LOGITS
     MGM
    2.74
     Mosque
    2.68
     Cinema
    2.64
     Magicka
    2.61
    Tickets
    2.60
     Theatre
    2.58
     MTV
    2.54
     NRS
    2.47
     Pepsi
    2.44
     Distribut
    2.42
    Activations Density 0.000%

    No Known Activations