© 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. 5-ATT-KK
    11. 27339
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.05
    3:0.15
    4:0.09
    5:0.05
    6:0.02
    7:0.05
    8:0.06
    9:0.12
    10:0.15
    11:0.16
    Negative Logits
     decre
    -1.50
     Baal
    -1.47
     incre
    -1.42
     Britann
    -1.40
     forb
    -1.40
     Hath
    -1.39
     tram
    -1.39
    ashtra
    -1.37
     deleg
    -1.36
     rule
    -1.34
    POSITIVE LOGITS
    CNN
    1.47
    cerpt
    1.44
     cryptocurrencies
    1.35
     ·
    1.35
    yrics
    1.35
    BD
    1.30
    usional
    1.30
     Transcript
    1.29
     trolling
    1.28
    onyms
    1.27
    Activations Density 0.026%

    No Known Activations