© 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. 8225
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate intention or purpose

    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
    0:0.05
    1:0.06
    2:0.13
    3:0.11
    4:0.02
    5:0.03
    6:0.10
    7:0.13
    8:0.06
    9:0.07
    10:0.14
    11:0.06
    Negative Logits
     Secrets
    -0.89
    turned
    -0.83
    anamo
    -0.82
    laden
    -0.77
     piled
    -0.77
     background
    -0.76
    gain
    -0.76
    jan
    -0.76
    Fast
    -0.76
    eled
    -0.75
    POSITIVE LOGITS
     IPM
    1.01
    uple
    0.90
    estine
    0.79
     deleg
    0.74
    renches
    0.74
    oreal
    0.74
     acknow
    0.73
    ormonal
    0.72
    trl
    0.72
    LINE
    0.72
    Activations Density 0.059%

    No Known Activations