© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 43878
    Prev
    Next
    INDEX
    Explanations

    distinct phonetic components or variations in words

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.05
    5:0.03
    6:0.52
    7:0.03
    8:0.04
    9:0.06
    10:0.06
    11:0.03
    Negative Logits
    oval
    -1.51
     ILCS
    -1.25
     showc
    -1.23
     Flags
    -1.19
     [*]
    -1.18
    mitt
    -1.14
    Maker
    -1.11
    olphin
    -1.11
     Jolly
    -1.10
    Cross
    -1.10
    POSITIVE LOGITS
    theless
    1.60
    TPPStreamerBot
    1.36
    シャ
    1.32
    stadt
    1.22
     obs
    1.21
    iqueness
    1.20
    ensical
    1.17
    baugh
    1.17
     filibuster
    1.15
    matter
    1.14
    Activations Density 0.003%

    No Known Activations