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. 14042
    Prev
    Next
    INDEX
    Explanations

    statistical relationships and correlations between different variables or factors

    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
    0:0.06
    1:0.03
    2:0.13
    3:0.06
    4:0.17
    5:0.08
    6:0.03
    7:0.04
    8:0.14
    9:0.11
    10:0.06
    11:0.03
    Negative Logits
    isode
    -1.29
    ikers
    -1.28
    wings
    -1.25
    haw
    -1.23
     ORDER
    -1.17
    nw
    -1.16
     captives
    -1.14
     gladly
    -1.13
    hearted
    -1.12
    boy
    -1.12
    POSITIVE LOGITS
     causation
    1.74
    govtrack
    1.44
     Analy
    1.39
     caus
    1.38
    ーテ
    1.37
    senal
    1.33
    ativity
    1.23
     GDP
    1.21
    ioxide
    1.21
     similarity
    1.19
    Activations Density 0.007%

    No Known Activations