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. 9592
    Prev
    Next
    INDEX
    Explanations

    words related to online tracking and privacy measures

    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
    0:0.04
    1:0.04
    2:0.01
    3:0.09
    4:0.04
    5:0.18
    6:0.09
    7:0.01
    8:0.35
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
     occupations
    -1.71
     demol
    -1.68
    ciation
    -1.67
    isans
    -1.67
     trench
    -1.66
     stret
    -1.64
     feud
    -1.64
     confrontation
    -1.62
     kindred
    -1.61
    ivably
    -1.59
    POSITIVE LOGITS
     expired
    2.09
     cookies
    1.99
     Cookies
    1.91
    activated
    1.86
    zed
    1.83
    aned
    1.78
     innocuous
    1.78
     expire
    1.76
    cookie
    1.73
     cookie
    1.72
    Activations Density 0.002%

    No Known Activations