© 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. 10-ATT-KK
    6. 13992
    Prev
    Next
    INDEX
    Explanations

    a specific named entity or individual referenced in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.07
    2:0.08
    3:0.08
    4:0.07
    5:0.07
    6:0.07
    7:0.08
    8:0.09
    9:0.08
    10:0.08
    11:0.09
    Negative Logits
     Brennan
    -2.85
    urrection
    -2.81
     Winged
    -2.77
    lehem
    -2.72
     Pelosi
    -2.62
    Shar
    -2.58
    INA
    -2.57
     Olsen
    -2.57
    rano
    -2.56
    idine
    -2.56
    POSITIVE LOGITS
     licences
    3.02
     apologised
    2.92
     Tasmania
    2.90
     licence
    2.72
     MPG
    2.57
    Bott
    2.55
     realised
    2.55
     Forums
    2.48
     realise
    2.47
    isable
    2.46
    Activations Density 0.000%

    No Known Activations