© 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. 5-ATT-KK
    6. 27676
    Prev
    Next
    INDEX
    Explanations

    the presence of punctuation and sentence structure elements in the text

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.11
    4:0.29
    5:0.03
    6:0.05
    7:0.11
    8:0.06
    9:0.05
    10:0.06
    11:0.06
    Negative Logits
    ppa
    -1.54
     Colomb
    -1.51
     psi
    -1.39
     Portuguese
    -1.29
     Sophia
    -1.21
     Cosmos
    -1.20
     Ancients
    -1.20
     Cham
    -1.18
     passage
    -1.18
     Bradley
    -1.17
    POSITIVE LOGITS
    etheless
    1.80
    foundland
    1.64
    """
    1.47
     Referred
    1.44
    insula
    1.43
    assador
    1.42
    seys
    1.40
    "]=>
    1.40
    owship
    1.36
     Retrieved
    1.36
    Activations Density 0.002%

    No Known Activations