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. 9-ATT-KK
    6. 7596
    Prev
    Next
    INDEX
    Explanations

    instances related to events and their temporal context, particularly regarding sports, political activities, and natural disasters

    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
    0:0.06
    1:0.01
    2:0.03
    3:0.12
    4:0.02
    5:0.07
    6:0.01
    7:0.06
    8:0.02
    9:0.02
    10:0.50
    11:0.02
    Negative Logits
     tomorrow
    -4.82
     tonight
    -3.72
     soon
    -3.53
     lately
    -3.40
     today
    -3.31
    today
    -3.13
    soon
    -3.08
     sometime
    -3.04
    morrow
    -2.97
    Thursday
    -2.96
    POSITIVE LOGITS
    zech
    2.11
     which
    1.89
    oided
    1.77
     Which
    1.75
    jection
    1.75
    Which
    1.73
    ansky
    1.72
    andem
    1.70
     Were
    1.70
    which
    1.65
    Activations Density 1.339%

    No Known Activations