© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 12419
    Prev
    Next
    INDEX
    Explanations

    occurrences of dates and times in various contexts

    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
    0:0.09
    1:0.11
    2:0.04
    3:0.16
    4:0.03
    5:0.03
    6:0.05
    7:0.13
    8:0.09
    9:0.03
    10:0.16
    11:0.02
    Negative Logits
     Spokane
    -3.03
     Lafayette
    -2.96
     Akron
    -2.84
     Grassley
    -2.81
     Delta
    -2.80
     Lansing
    -2.74
     Idaho
    -2.72
     Dickinson
    -2.72
     Hawaiian
    -2.71
     liv
    -2.71
    POSITIVE LOGITS
     (£
    3.97
     organis
    3.95
     recognise
    3.88
    £
    3.85
     organisers
    3.69
     organising
    3.64
     £
    3.60
     Nato
    3.53
     authorised
    3.44
     realise
    3.44
    Activations Density 0.012%

    No Known Activations