© 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. 43671
    Prev
    Next
    INDEX
    Explanations

    questions related to decision-making, planning, and evaluation of performance in various contexts

    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
    0:0.12
    1:0.04
    2:0.07
    3:0.19
    4:0.06
    5:0.07
    6:0.04
    7:0.06
    8:0.07
    9:0.09
    10:0.07
    11:0.08
    Negative Logits
    ↵ 
    -1.50
    ribune
    -1.42
     doesnt
    -1.40
    rompt
    -1.32
    pmwiki
    -1.30
     File
    -1.25
    wx
    -1.22
     ):
    -1.22
     padd
    -1.22
    laughs
    -1.20
    POSITIVE LOGITS
    )?
    1.67
    ?'"
    1.53
    '?
    1.50
    ?
    1.45
    emia
    1.39
    ?'
    1.33
    ?).
    1.30
    interstitial
    1.30
     vouchers
    1.26
     assistants
    1.20
    Activations Density 0.092%

    No Known Activations