© 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. 3-ATT-KK
    11. 10616
    Prev
    Next
    INDEX
    Explanations

    transcripts and associated metadata related to documents or media segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.11
    2:0.07
    3:0.04
    4:0.04
    5:0.14
    6:0.09
    7:0.09
    8:0.09
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    represented
    -1.77
    aimon
    -1.66
    gdala
    -1.64
    pora
    -1.53
    byss
    -1.52
     meanwhile
    -1.47
    hedon
    -1.47
    conservancy
    -1.46
    gat
    -1.45
    gars
    -1.44
    POSITIVE LOGITS
     reader
    1.46
     photoc
    1.43
     delivery
    1.33
    �
    1.33
     takeoff
    1.33
     typew
    1.32
    ...]
    1.27
     transcripts
    1.23
     newsp
    1.22
    .")
    1.21
    Activations Density 0.001%

    No Known Activations