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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 3-ATT-KK
    6. 7956
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries related to opinions and decision-making

    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
    0:0.02
    1:0.08
    2:0.04
    3:0.01
    4:0.02
    5:0.14
    6:0.05
    7:0.03
    8:0.05
    9:0.38
    10:0.06
    11:0.05
    Negative Logits
    irtual
    -1.72
    knit
    -1.72
    EStreamFrame
    -1.52
    ön
    -1.51
    Catalog
    -1.50
     Thumbnails
    -1.49
    AMY
    -1.46
     starve
    -1.46
    nown
    -1.45
    elin
    -1.43
    POSITIVE LOGITS
    answer
    1.64
     aloud
    1.50
     hes
    1.36
     Tus
    1.34
    essor
    1.33
     adequ
    1.33
     Clare
    1.32
     seriousness
    1.31
    worthiness
    1.30
     methodology
    1.29
    Activations Density 0.015%

    No Known Activations