© 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. 3-ATT-KK
    6. 8234
    Prev
    Next
    INDEX
    Explanations

    themes related to funding and support for various causes and organizations

    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
    0:0.01
    1:0.03
    2:0.17
    3:0.10
    4:0.01
    5:0.02
    6:0.08
    7:0.14
    8:0.09
    9:0.17
    10:0.08
    11:0.05
    Negative Logits
     unveiling
    -1.00
     demonstrating
    -0.95
     outing
    -0.95
    ′
    -0.87
     1961
    -0.86
     demonstration
    -0.85
     boasting
    -0.84
     surprisingly
    -0.84
     Bearing
    -0.83
     teasing
    -0.83
    POSITIVE LOGITS
    endas
    1.30
    thood
    1.25
    doms
    1.21
    soDeliveryDate
    1.21
    DIT
    1.14
    ドラ
    1.13
    ieties
    1.01
    rients
    1.00
    ictionary
    0.99
    uci
    0.99
    Activations Density 0.511%

    No Known Activations