© 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. 2-ATT-KK
    11. 23230
    Prev
    Next
    INDEX
    Explanations

    phrases related to various unrelated topics including medical information, professional services, historical events, and personal preferences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    names of prominent companies or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.02
    2:0.06
    3:0.12
    4:0.03
    5:0.13
    6:0.04
    7:0.07
    8:0.13
    9:0.04
    10:0.14
    11:0.07
    Negative Logits
    formance
    -0.96
    creen
    -0.89
    exempt
    -0.88
    berra
    -0.88
     paranormal
    -0.86
     enclave
    -0.84
    osterone
    -0.84
     partName
    -0.83
    ベ
    -0.83
    geist
    -0.82
    POSITIVE LOGITS
    OTOS
    1.01
    BB
    0.98
    llo
    0.89
    inea
    0.88
     Pier
    0.87
    /+
    0.86
    Pir
    0.85
    Wave
    0.85
    RA
    0.85
     Pirate
    0.84
    Activations Density 0.253%

    No Known Activations