© 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. 5-ATT-KK
    6. 27638
    Prev
    Next
    INDEX
    Explanations

    phrases expressing significant economic or health impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.01
    2:0.09
    3:0.05
    4:0.15
    5:0.04
    6:0.09
    7:0.20
    8:0.05
    9:0.04
    10:0.11
    11:0.10
    Negative Logits
    hari
    -1.55
    BuyableInstoreAndOnline
    -1.53
     eyed
    -1.47
    obbies
    -1.43
    ected
    -1.41
    abee
    -1.41
    romy
    -1.36
    guyen
    -1.32
    anooga
    -1.30
    igers
    -1.27
    POSITIVE LOGITS
     impacting
    1.63
     impact
    1.52
     affecting
    1.51
     Meaning
    1.42
    ulative
    1.40
    sic
    1.39
     negatively
    1.38
     affect
    1.35
     Nationwide
    1.29
    pace
    1.27
    Activations Density 0.011%

    No Known Activations