© 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. 5-ATT-KK
    11. 8228
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to galaxies and their interactions

    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
    2:0.05
    3:0.06
    4:0.03
    5:0.07
    6:0.03
    7:0.02
    8:0.03
    9:0.12
    10:0.31
    11:0.20
    Negative Logits
     LAW
    -1.29
    ollo
    -1.15
     Melania
    -1.14
    valid
    -1.12
    IU
    -1.10
    beam
    -1.10
    apore
    -1.08
    orgetown
    -1.08
    office
    -1.08
     ADA
    -1.08
    POSITIVE LOGITS
     Siber
    1.27
     dying
    1.14
    doms
    1.13
    versions
    1.11
     stockp
    1.10
     quarry
    1.09
     collapsing
    1.07
    killing
    1.07
     killers
    1.05
     clust
    1.04
    Activations Density 0.020%

    No Known Activations