© 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. 43009
    Prev
    Next
    INDEX
    Explanations

    vowel-heavy word fragments and suffixes

    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
    0:0.03
    1:0.01
    2:0.08
    3:0.06
    4:0.06
    5:0.03
    6:0.41
    7:0.07
    8:0.04
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    APS
    -1.38
    WAY
    -1.37
    oad
    -1.34
     disclaimer
    -1.28
    Quantity
    -1.28
    �
    -1.27
    Dash
    -1.26
    onom
    -1.24
    Reply
    -1.23
     clipboard
    -1.22
    POSITIVE LOGITS
    achus
    1.29
     horizont
    1.28
    quartered
    1.23
    ]}
    1.22
    afort
    1.22
     Zot
    1.21
    orgetown
    1.18
    aukee
    1.17
    quart
    1.17
    ropolitan
    1.17
    Activations Density 0.015%

    No Known Activations