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. 9511
    Prev
    Next
    INDEX
    Explanations

    phrases that involve quantitative relationships or measurements

    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
    0:0.20
    1:0.07
    2:0.02
    3:0.14
    4:0.04
    5:0.06
    6:0.09
    7:0.01
    8:0.20
    9:0.09
    10:0.01
    11:0.02
    Negative Logits
    Downloadha
    -1.74
     beginnings
    -1.69
    DoS
    -1.66
    olis
    -1.62
    aution
    -1.62
    ascript
    -1.61
    ahime
    -1.61
    antry
    -1.61
     conduc
    -1.61
     juggling
    -1.61
    POSITIVE LOGITS
     Radical
    1.56
     Pin
    1.56
     Deep
    1.52
     favourite
    1.48
     Forgotten
    1.47
     Hearts
    1.43
     Strange
    1.39
     iconic
    1.37
     favorite
    1.37
     Toro
    1.36
    Activations Density 0.014%

    No Known Activations