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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14707
    Prev
    Next
    INDEX
    Explanations

    discussions around the concept of freedom and its different interpretations

    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
    0:0.10
    1:0.14
    2:0.05
    3:0.07
    4:0.09
    5:0.02
    6:0.16
    7:0.11
    8:0.02
    9:0.04
    10:0.04
    11:0.10
    Negative Logits
     Cosponsors
    -2.56
     cas
    -2.51
    abase
    -2.50
     HEAD
    -2.40
    LCS
    -2.38
    alli
    -2.34
     Soup
    -2.34
    ovember
    -2.28
     Navajo
    -2.27
    ecycle
    -2.26
    POSITIVE LOGITS
     freedom
    6.84
     liberty
    6.77
    freedom
    6.57
     freedoms
    6.38
    Freedom
    5.82
     Freedom
    5.41
     liberties
    4.96
     liberate
    4.75
     Liberty
    4.64
    liber
    4.61
    Activations Density 0.053%

    No Known Activations