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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8348
    Prev
    Next
    INDEX
    Explanations

    references to age or time-related attributes

    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
    1:0.05
    2:0.06
    3:0.10
    4:0.02
    5:0.04
    6:0.04
    7:0.11
    8:0.08
    9:0.21
    10:0.06
    11:0.16
    Negative Logits
    eligible
    -1.57
    Updated
    -1.43
     depended
    -1.36
     strapped
    -1.28
    soever
    -1.26
    tops
    -1.25
    });
    -1.25
     depends
    -1.24
    odder
    -1.23
     taxp
    -1.20
    POSITIVE LOGITS
     Cellular
    1.30
     causation
    1.25
    ural
    1.23
     Sas
    1.20
     Pattern
    1.17
     mislead
    1.16
    iom
    1.16
     sensation
    1.16
     phenomenon
    1.14
    ulpt
    1.12
    Activations Density 0.003%

    No Known Activations