Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 10102
    Prev
    Next
    INDEX
    Explanations

    the concept of "something" in various contexts and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.05
    2:0.25
    3:0.03
    4:0.03
    5:0.04
    6:0.11
    7:0.08
    8:0.04
    9:0.07
    10:0.12
    11:0.07
    Negative Logits
    lement
    -1.42
     IMAGES
    -1.08
    oppers
    -1.07
    berus
    -1.05
    heit
    -1.05
    ippers
    -1.02
    enegger
    -1.01
     Strait
    -0.99
    aths
    -0.98
    lings
    -0.98
    POSITIVE LOGITS
    マ
    1.21
     else
    1.00
    WithNo
    0.92
    Untitled
    0.90
     provisional
    0.90
    uine
    0.89
    anooga
    0.89
    dimension
    0.89
     somewhere
    0.88
    Balance
    0.86
    Activations Density 0.043%

    No Known Activations