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. 18814
    Prev
    Next
    INDEX
    Explanations

    references to social media interactions, particularly involving Twitter handles

    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
    1:0.02
    2:0.00
    3:0.05
    4:0.05
    5:0.25
    6:0.04
    7:0.02
    8:0.31
    9:0.11
    10:0.04
    11:0.02
    Negative Logits
     virginity
    -2.06
     indemn
    -1.88
     Affect
    -1.87
     Plaint
    -1.86
     backdrop
    -1.84
     inconvenience
    -1.80
     shareholders
    -1.79
     inconven
    -1.79
     uproar
    -1.78
     transpired
    -1.77
    POSITIVE LOGITS
    hower
    2.01
    rosso
    1.88
    jong
    1.86
     profiles
    1.85
    arthy
    1.82
    Coach
    1.81
    bart
    1.78
    HAEL
    1.78
    alli
    1.73
    ritz
    1.71
    Activations Density 0.005%

    No Known Activations