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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 46017
    Prev
    Next
    INDEX
    Explanations

    references to climate change

    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
    0:0.03
    1:0.03
    2:0.07
    3:0.05
    4:0.06
    5:0.04
    6:0.13
    7:0.06
    8:0.04
    9:0.07
    10:0.29
    11:0.09
    Negative Logits
     PAGE
    -2.10
    ULTS
    -1.84
    ONY
    -1.80
    blance
    -1.72
     BCC
    -1.71
    Cole
    -1.68
    ILLE
    -1.68
     Kers
    -1.66
    oldemort
    -1.66
     Corpse
    -1.62
    POSITIVE LOGITS
     Chaser
    2.08
    peace
    1.89
     apocalypse
    1.80
    engineering
    1.70
    technology
    1.66
    freedom
    1.66
     captivity
    1.62
    orbit
    1.61
    bending
    1.58
     Apart
    1.57
    Activations Density 0.005%

    No Known Activations