© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10497
    Prev
    Next
    INDEX
    Explanations

    temporal phrases related to duration and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.03
    2:0.06
    3:0.11
    4:0.05
    5:0.06
    6:0.04
    7:0.08
    8:0.07
    9:0.02
    10:0.34
    11:0.03
    Negative Logits
     Catch
    -1.98
     immensely
    -1.84
    Tumblr
    -1.77
     every
    -1.75
     hars
    -1.73
     increasingly
    -1.71
     core
    -1.71
     compliance
    -1.70
     disproportionately
    -1.69
     worldwide
    -1.68
    POSITIVE LOGITS
     ago
    3.36
     Ago
    3.14
     afterwards
    2.98
    seconds
    2.96
     later
    2.84
     beforehand
    2.82
     Months
    2.78
     afterward
    2.77
    months
    2.63
     shortly
    2.63
    Activations Density 0.091%

    No Known Activations