© 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. 19804
    Prev
    Next
    INDEX
    Explanations

    mentions of time and frequency-related concepts

    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
    0:0.07
    1:0.03
    2:0.06
    3:0.08
    4:0.15
    5:0.11
    6:0.03
    7:0.25
    8:0.04
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
     tox
    -2.05
     gastro
    -1.94
    urated
    -1.92
     corros
    -1.91
     pse
    -1.91
     ana
    -1.88
     resusc
    -1.86
     compr
    -1.86
     retarded
    -1.86
     externalToEVAOnly
    -1.84
    POSITIVE LOGITS
    Below
    2.71
    Please
    2.62
     Feel
    2.62
     🙂
    2.61
    <|endoftext|>
    2.53
    Advertisements
    2.45
    Hopefully
    2.43
    Enjoy
    2.39
    Each
    2.36
    [/
    2.34
    Activations Density 0.337%

    No Known Activations