© 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. 41979
    Prev
    Next
    INDEX
    Explanations

    numerical data associated with age demographics

    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
    0:0.06
    1:0.01
    2:0.19
    3:0.04
    4:0.05
    5:0.03
    6:0.10
    7:0.14
    8:0.06
    9:0.03
    10:0.11
    11:0.13
    Negative Logits
     encour
    -1.71
    izations
    -1.70
     suggestion
    -1.50
     suggestions
    -1.50
    measures
    -1.48
    isations
    -1.43
    Request
    -1.42
     advisors
    -1.41
     ACTIONS
    -1.38
    iological
    -1.37
    POSITIVE LOGITS
    terday
    1.74
    brance
    1.69
     Beetle
    1.65
    ounter
    1.59
    arel
    1.59
    anwhile
    1.57
    ylan
    1.54
     QC
    1.45
     Ascension
    1.43
     GOODMAN
    1.40
    Activations Density 0.002%

    No Known Activations