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. 7-ATT-KK
    6. 9466
    Prev
    Next
    INDEX
    Explanations

    time-related indications or timestamps in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.04
    2:0.05
    3:0.05
    4:0.01
    5:0.05
    6:0.09
    7:0.08
    8:0.09
    9:0.02
    10:0.20
    11:0.21
    Negative Logits
    �
    -2.34
    �
    -2.18
     Elephant
    -2.14
    edIn
    -2.12
    ahime
    -2.11
    chester
    -2.02
    atown
    -1.89
    Scotland
    -1.85
     eleph
    -1.83
    �
    -1.83
    POSITIVE LOGITS
     GOOD
    2.02
    htaking
    1.96
     consum
    1.89
     prototyp
    1.88
     VERY
    1.72
    browser
    1.70
     CLIENT
    1.69
     ripe
    1.66
    successful
    1.66
     REST
    1.63
    Activations Density 0.000%

    No Known Activations