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. 3-ATT-KK
    6. 8316
    Prev
    Next
    INDEX
    Explanations

    phrases related to police activity and investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.05
    2:0.08
    3:0.03
    4:0.03
    5:0.14
    6:0.24
    7:0.08
    8:0.07
    9:0.05
    10:0.08
    11:0.07
    Negative Logits
     reson
    -1.58
     conson
    -1.52
     Spir
    -1.47
     metaphor
    -1.40
     sung
    -1.37
     sang
    -1.35
     translated
    -1.34
     Protoss
    -1.33
     OECD
    -1.33
    ankind
    -1.31
    POSITIVE LOGITS
     surveillance
    1.72
     suspic
    1.69
     lookout
    1.67
     ATF
    1.64
     informants
    1.63
     custody
    1.62
     ABE
    1.62
    resp
    1.61
    reports
    1.58
    nsic
    1.56
    Activations Density 0.121%

    No Known Activations