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. 10306
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest comparison or a relationship between different elements

    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
    0:0.01
    1:0.03
    2:0.11
    3:0.03
    4:0.01
    5:0.03
    6:0.03
    7:0.02
    8:0.04
    9:0.53
    10:0.04
    11:0.05
    Negative Logits
    buster
    -1.34
    aliation
    -1.25
     cure
    -1.20
    acea
    -1.17
    itle
    -1.15
    �
    -1.15
     royalty
    -1.14
    oother
    -1.13
    ////////
    -1.12
    }}
    -1.11
    POSITIVE LOGITS
     onwards
    1.77
     standpoint
    1.75
    ebook
    1.69
    DragonMagazine
    1.55
     vantage
    1.46
     backgrounds
    1.42
    lems
    1.41
     perspective
    1.35
    anges
    1.33
     reperto
    1.32
    Activations Density 0.321%

    No Known Activations