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. 5-ATT-KK
    6. 44352
    Prev
    Next
    INDEX
    Explanations

    phrases related to categories of discrimination and animal rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+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.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.09
    3:0.08
    4:0.13
    5:0.04
    6:0.13
    7:0.27
    8:0.04
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
    govtrack
    -1.63
     favorites
    -1.55
     priority
    -1.52
     successes
    -1.50
    fman
    -1.41
     planners
    -1.40
     favourites
    -1.39
     directing
    -1.38
    liest
    -1.38
     enroll
    -1.38
    POSITIVE LOGITS
     Animals
    1.68
    Beast
    1.57
     Sacred
    1.54
     Mamm
    1.51
     Terrorism
    1.51
     Corruption
    1.50
     Violence
    1.50
     Atmosp
    1.48
     Memory
    1.44
     Cruel
    1.44
    Activations Density 0.003%

    No Known Activations