© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3109
    Prev
    Next
    INDEX
    Explanations

    references to notable events or milestones in a chronological context

    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
    0:0.01
    1:0.01
    2:0.27
    3:0.12
    4:0.11
    5:0.02
    6:0.05
    7:0.04
    8:0.05
    9:0.03
    10:0.13
    11:0.10
    Negative Logits
    vic
    -1.41
    ersen
    -1.34
    rand
    -1.32
    ���
    -1.31
    onyms
    -1.30
    arm
    -1.28
    orget
    -1.25
    ngth
    -1.21
    xual
    -1.20
    ité
    -1.20
    POSITIVE LOGITS
     postponed
    1.64
     adjourn
    1.55
     testament
    1.54
     postp
    1.51
     continuation
    1.50
     celebration
    1.39
    ursday
    1.37
     backdrop
    1.36
     fres
    1.33
    contin
    1.33
    Activations Density 0.191%

    No Known Activations