© 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. 28093
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and significant names

    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
    0:0.09
    1:0.22
    2:0.03
    3:0.03
    4:0.05
    5:0.23
    6:0.14
    7:0.01
    8:0.04
    9:0.05
    10:0.04
    11:0.02
    Negative Logits
     imag
    -1.80
    anyl
    -1.60
     photograp
    -1.45
     matt
    -1.41
     downloading
    -1.40
     topp
    -1.37
     obser
    -1.36
     haste
    -1.34
     fantas
    -1.34
     experien
    -1.33
    POSITIVE LOGITS
    eez
    1.65
    isphere
    1.50
    essen
    1.47
    leans
    1.45
    owitz
    1.44
    naires
    1.44
    ette
    1.44
    ettes
    1.40
    ospels
    1.40
    inator
    1.39
    Activations Density 0.174%

    No Known Activations