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. 14684
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a critical perspective on institutions or situations

    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
    0:0.07
    1:0.08
    2:0.07
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.09
    8:0.07
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
    uber
    -2.60
    keyes
    -2.60
    76561
    -2.52
    ppel
    -2.52
    esp
    -2.45
     Blizz
    -2.44
    oo
    -2.42
    reau
    -2.31
    ャ
    -2.29
    usercontent
    -2.29
    POSITIVE LOGITS
    incerity
    2.54
    ���
    2.39
     uncovered
    2.36
    RIC
    2.35
    eteria
    2.31
     carts
    2.31
    istor
    2.29
     rudimentary
    2.27
    unta
    2.26
     schematic
    2.25
    Activations Density 0.000%

    No Known Activations