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. 7097
    Prev
    Next
    INDEX
    Explanations

    words related to observance or adherence to rules or traditions

    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
    2:0.08
    3:0.04
    4:0.11
    5:0.03
    6:0.05
    7:0.31
    8:0.02
    9:0.03
    10:0.16
    11:0.08
    Negative Logits
    reau
    -1.74
    anooga
    -1.72
    rolet
    -1.60
    arnaev
    -1.52
    orge
    -1.43
    ulton
    -1.41
     recru
    -1.40
    esan
    -1.38
    rill
    -1.37
    akespe
    -1.36
    POSITIVE LOGITS
     curfew
    2.03
     observ
    1.75
    Temperature
    1.56
     observations
    1.55
     observing
    1.53
     holiday
    1.50
     observation
    1.49
     watches
    1.48
     observe
    1.47
     blackout
    1.47
    Activations Density 0.000%

    No Known Activations