© 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. 45051
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or measurement

    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
    1:0.01
    2:0.05
    3:0.06
    4:0.06
    5:0.03
    6:0.16
    7:0.25
    8:0.02
    9:0.04
    10:0.05
    11:0.19
    Negative Logits
    hig
    -1.43
    merce
    -1.42
    iasm
    -1.39
    aler
    -1.39
    andise
    -1.38
    cean
    -1.37
    ester
    -1.36
    nces
    -1.35
    orate
    -1.33
    gently
    -1.29
    POSITIVE LOGITS
     casualties
    1.42
     survivors
    1.37
     offenders
    1.35
     participants
    1.29
     beneficiaries
    1.27
     syll
    1.25
    CB
    1.24
     drawbacks
    1.23
     cere
    1.23
     trib
    1.22
    Activations Density 0.015%

    No Known Activations