© 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. 35965
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information associated with events or occurrences

    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
    0:0.04
    1:0.01
    2:0.12
    3:0.04
    4:0.16
    5:0.04
    6:0.09
    7:0.04
    8:0.17
    9:0.03
    10:0.08
    11:0.11
    Negative Logits
    76561
    -1.64
    ィ
    -1.38
     bigot
    -1.34
    ARE
    -1.31
     disav
    -1.31
     Ug
    -1.26
    />
    -1.25
     misinterpret
    -1.25
    $$
    -1.22
     understatement
    -1.21
    POSITIVE LOGITS
    opolis
    1.56
    unin
    1.53
    worms
    1.52
    cade
    1.52
    depending
    1.51
    ubis
    1.44
    hus
    1.44
    zl
    1.42
    zhou
    1.41
     Geh
    1.41
    Activations Density 0.007%

    No Known Activations