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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19274
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and protests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    2:0.07
    3:0.04
    4:0.13
    5:0.02
    6:0.04
    7:0.39
    8:0.02
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
    arnaev
    -1.70
     Trop
    -1.47
    illac
    -1.47
    ategory
    -1.47
    utical
    -1.45
    afort
    -1.43
    perture
    -1.43
    foundation
    -1.41
     Panama
    -1.41
     Americas
    -1.40
    POSITIVE LOGITS
     passers
    2.21
     loudly
    1.91
     incess
    1.79
     aloud
    1.75
     loud
    1.73
     noises
    1.66
     laughter
    1.63
     praises
    1.60
     louder
    1.58
     neigh
    1.56
    Activations Density 0.110%

    No Known Activations