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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 7-ATT-KK
    6. 18974
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters

    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
    2:0.03
    3:0.23
    4:0.08
    5:0.08
    6:0.05
    7:0.03
    8:0.09
    9:0.17
    10:0.04
    11:0.04
    Negative Logits
    Updated
    -1.73
    Assembly
    -1.59
    aturday
    -1.54
     TODAY
    -1.54
     Enlightenment
    -1.54
    Atlanta
    -1.52
     TheNitromeFan
    -1.51
    Bull
    -1.51
     BIT
    -1.50
     Aston
    -1.48
    POSITIVE LOGITS
    assad
    2.24
     linem
    1.96
    ogene
    1.96
    untled
    1.93
     eleph
    1.93
    anded
    1.85
    覚醒
    1.82
    】
    1.81
    esides
    1.80
    hands
    1.75
    Activations Density 0.000%

    No Known Activations