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. 10-ATT-KK
    6. 14626
    Prev
    Next
    INDEX
    Explanations

    references to data or applications, particularly those related to potential data leaks or vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.22
    1:0.19
    2:0.03
    3:0.06
    4:0.04
    5:0.03
    6:0.07
    7:0.13
    8:0.03
    9:0.03
    10:0.08
    11:0.04
    Negative Logits
     Heller
    -3.49
     Atom
    -2.86
     Byrd
    -2.83
     Ukrain
    -2.71
     McCarthy
    -2.66
     Feldman
    -2.59
    rina
    -2.54
     homophobic
    -2.52
    obyl
    -2.49
     posit
    -2.47
    POSITIVE LOGITS
    une
    4.77
    UNE
    4.22
    uning
    3.71
    unes
    3.67
     sand
    3.05
    cients
    2.99
    uned
    2.85
    acci
    2.81
     sequ
    2.76
    imus
    2.75
    Activations Density 0.001%

    No Known Activations