© 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. 44578
    Prev
    Next
    INDEX
    Explanations

    temperature-related data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.08
    1:0.10
    2:0.05
    3:0.04
    4:0.03
    5:0.20
    6:0.06
    7:0.06
    8:0.11
    9:0.07
    10:0.09
    11:0.06
    Negative Logits
    netflix
    -1.62
    rawdownloadcloneembedreportprint
    -1.57
     curated
    -1.57
     guiActiveUn
    -1.57
     homegrown
    -1.55
     kits
    -1.53
     NCT
    -1.52
    Reviewer
    -1.51
     proto
    -1.49
     unborn
    -1.48
    POSITIVE LOGITS
    Earth
    1.96
    Ct
    1.85
    Distance
    1.85
    E
    1.73
     Winds
    1.66
    P
    1.61
    nings
    1.60
    XP
    1.60
    Euro
    1.57
     Indra
    1.56
    Activations Density 0.001%

    No Known Activations