© 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. 2643
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation marks in text

    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
    0:0.06
    1:0.03
    2:0.05
    3:0.04
    4:0.06
    5:0.03
    6:0.20
    7:0.05
    8:0.10
    9:0.26
    10:0.02
    11:0.05
    Negative Logits
     BART
    -4.32
    ober
    -3.89
     BB
    -3.75
     Bot
    -3.72
     bot
    -3.66
     cellul
    -3.66
    bart
    -3.65
     Pub
    -3.55
     Buch
    -3.53
     ecc
    -3.52
    POSITIVE LOGITS
     Hassan
    10.85
     Hasan
    7.14
     Hussein
    6.92
     Hussain
    6.89
     Mous
    5.59
    sein
    5.09
     Nas
    4.96
     Hamm
    4.55
     Rahman
    4.52
     Amir
    4.42
    Activations Density 0.001%

    No Known Activations