© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 620
    Prev
    Next
    INDEX
    Explanations

    references to various demographics and their needs within societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    2:0.08
    3:0.21
    4:0.03
    5:0.11
    6:0.03
    7:0.04
    8:0.02
    9:0.01
    10:0.31
    11:0.04
    Negative Logits
    senal
    -1.93
    THING
    -1.92
    inventoryQuantity
    -1.90
    verb
    -1.88
     gore
    -1.87
    "))
    -1.77
     fumble
    -1.76
    elsen
    -1.73
    Fake
    -1.73
     plum
    -1.68
    POSITIVE LOGITS
     irrespective
    2.75
     regardless
    2.70
     alike
    2.42
     while
    2.39
     whilst
    2.38
     whereas
    2.29
     alongside
    2.28
     Residents
    2.15
     whom
    2.10
     along
    2.07
    Activations Density 0.247%

    No Known Activations