© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22887
    Prev
    Next
    INDEX
    Explanations

    time-related information, such as specific durations like years, weeks, months, and days

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

    quantities or measurements related to time and duration

    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
    0:0.12
    1:0.03
    2:0.07
    3:0.10
    4:0.32
    5:0.06
    6:0.03
    7:0.02
    8:0.05
    9:0.06
    10:0.06
    11:0.02
    Negative Logits
    opia
    -1.48
    pred
    -1.42
     Rath
    -1.36
     Trave
    -1.36
    cal
    -1.33
     Cyn
    -1.29
    Chel
    -1.27
     Doodle
    -1.27
     Riders
    -1.27
     Zi
    -1.26
    POSITIVE LOGITS
    ega
    1.52
     dozen
    1.52
     resume
    1.47
    ithub
    1.47
     gigs
    1.45
    kick
    1.43
    dozen
    1.42
     evenings
    1.41
    drop
    1.39
    cipline
    1.38
    Activations Density 0.010%

    No Known Activations