© 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. 10-ATT-KK
    11. 8561
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with dates or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    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
    2:0.04
    3:0.05
    4:0.11
    5:0.07
    6:0.03
    7:0.05
    8:0.40
    9:0.06
    10:0.03
    11:0.05
    Negative Logits
    /#
    -2.82
     ende
    -2.56
     mathemat
    -2.51
     neighb
    -2.44
     arrang
    -2.43
     warr
    -2.41
     proport
    -2.40
    ccording
    -2.34
     artif
    -2.32
     fundament
    -2.32
    POSITIVE LOGITS
    Poké
    2.39
    bow
    2.16
    rue
    2.15
    endo
    2.12
    sylv
    2.12
    laughs
    2.05
    Cola
    2.04
    Semitic
    2.00
    elson
    2.00
    Donald
    2.00
    Activations Density 0.032%

    No Known Activations