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. 10-ATT-KK
    6. 14531
    Prev
    Next
    INDEX
    Explanations

    references to the 1960s

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.07
    6:0.07
    7:0.09
    8:0.08
    9:0.08
    10:0.10
    11:0.07
    Negative Logits
    $$
    -3.08
     diagonal
    -2.79
    ija
    -2.68
     Nou
    -2.66
     tremend
    -2.57
    nox
    -2.56
    POST
    -2.54
     dots
    -2.52
     Nad
    -2.51
     viz
    -2.51
    POSITIVE LOGITS
     Texans
    2.96
    Dialogue
    2.74
    ‎
    2.72
    Bah
    2.64
     barbecue
    2.63
     Morty
    2.61
     Sentinel
    2.46
     Houston
    2.42
     Healing
    2.39
     Moff
    2.39
    Activations Density 0.000%

    No Known Activations