Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10689
    Prev
    Next
    INDEX
    Explanations

    patterns related to fundraising or support efforts

    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
    1:0.07
    2:0.10
    3:0.15
    4:0.04
    5:0.05
    6:0.12
    7:0.13
    8:0.05
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
     confir
    -1.59
     redes
    -1.10
    gain
    -1.07
    idays
    -1.06
     timeframe
    -1.05
     favourable
    -1.02
     redress
    -1.02
    龍契士
    -1.01
    aido
    -1.01
    event
    -1.00
    POSITIVE LOGITS
    Tes
    1.06
     spat
    1.04
     spray
    0.99
    {"
    0.96
     choked
    0.95
     Paste
    0.95
    iform
    0.94
    etsy
    0.94
    itia
    0.94
    eless
    0.94
    Activations Density 0.001%

    No Known Activations