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. 2-ATT-KK
    6. 13862
    Prev
    Next
    INDEX
    Explanations

    terms related to rhythms and cycles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.20
    3:0.04
    4:0.17
    5:0.06
    6:0.04
    7:0.03
    8:0.08
    9:0.17
    10:0.06
    11:0.03
    Negative Logits
    egu
    -1.45
    skirts
    -1.41
    ilts
    -1.41
     indemn
    -1.41
    �士
    -1.30
    iaries
    -1.29
     Dign
    -1.26
    urtles
    -1.22
     Fasc
    -1.21
    iances
    -1.21
    POSITIVE LOGITS
    drive
    1.33
     sorcery
    1.25
    actic
    1.25
    repeat
    1.25
    Round
    1.21
     rounds
    1.20
     shootout
    1.16
     Alto
    1.15
     folklore
    1.15
     thriller
    1.13
    Activations Density 0.003%

    No Known Activations