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. 14623
    Prev
    Next
    INDEX
    Explanations

    quantities and specific numerical values associated with entities or events

    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
    0:0.06
    1:0.23
    2:0.06
    3:0.11
    4:0.04
    5:0.02
    6:0.16
    7:0.07
    8:0.04
    9:0.04
    10:0.09
    11:0.04
    Negative Logits
    NRS
    -3.14
    south
    -2.89
     horizont
    -2.87
     Huck
    -2.59
    soType
    -2.59
     Winc
    -2.57
    Pitt
    -2.57
    illery
    -2.48
     Spiel
    -2.44
     GOODMAN
    -2.43
    POSITIVE LOGITS
    Prime
    7.32
     Prime
    7.25
    prime
    6.44
     prime
    6.41
     PM
    3.42
     premier
    3.40
     Trudeau
    3.34
     Premiere
    3.22
    IME
    3.18
     Prim
    3.07
    Activations Density 0.013%

    No Known Activations