© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12725
    Prev
    Next
    INDEX
    Explanations

    references to climate change and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.04
    2:0.20
    3:0.07
    4:0.10
    5:0.05
    6:0.12
    7:0.09
    8:0.08
    9:0.06
    10:0.03
    11:0.04
    Negative Logits
    byter
    -2.90
     Fn
    -2.65
     onstage
    -2.61
     vendor
    -2.59
    swick
    -2.58
    Interstitial
    -2.54
     Weasley
    -2.51
    ��
    -2.46
    hemy
    -2.46
     handcuffs
    -2.45
    POSITIVE LOGITS
     glaciers
    5.09
    Climate
    4.67
     Glac
    4.59
     Antarctic
    4.54
     glacier
    4.54
     Antarctica
    4.50
     sediment
    4.44
     geological
    4.42
     biologists
    4.35
     algae
    4.30
    Activations Density 0.230%

    No Known Activations