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. 7645
    Prev
    Next
    INDEX
    Explanations

    names of people associated with various contexts

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.23
    4:0.02
    5:0.02
    6:0.14
    7:0.16
    8:0.04
    9:0.08
    10:0.08
    11:0.05
    Negative Logits
     juices
    -1.30
    amia
    -1.15
    matically
    -1.08
    tera
    -1.04
     Healer
    -1.00
     positively
    -0.99
    aneously
    -0.97
    elight
    -0.96
     Disciple
    -0.96
    anos
    -0.96
    POSITIVE LOGITS
    aley
    1.21
     Jr
    1.07
    ale
    1.06
    lein
    1.04
     Laboratories
    1.02
     Pearce
    0.98
     germ
    0.98
    stad
    0.98
     gib
    0.98
    mile
    0.97
    Activations Density 0.007%

    No Known Activations