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. 7-ATT-KK
    6. 9486
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency or repetition in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.34
    1:0.03
    2:0.00
    3:0.08
    4:0.03
    5:0.06
    6:0.07
    7:0.04
    8:0.22
    9:0.04
    10:0.01
    11:0.02
    Negative Logits
    ffen
    -1.88
    issance
    -1.73
    found
    -1.73
    ronics
    -1.73
    ECD
    -1.66
    ahi
    -1.66
    affe
    -1.63
    apo
    -1.60
    ITCH
    -1.59
    DCS
    -1.59
    POSITIVE LOGITS
     eternity
    1.79
     leash
    1.76
     tides
    1.74
    ruary
    1.71
    rily
    1.70
     innings
    1.70
     divid
    1.67
     day
    1.61
     cooldown
    1.60
    eday
    1.59
    Activations Density 0.005%

    No Known Activations