© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 39477
    Prev
    Next
    INDEX
    Explanations

    content that emphasizes news and updates relevant to a specific audience

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.11
    3:0.12
    4:0.37
    5:0.01
    6:0.03
    7:0.10
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
     aside
    -1.46
     IE
    -1.40
    esters
    -1.35
     testified
    -1.34
    uler
    -1.34
     countered
    -1.31
    itors
    -1.31
     sshd
    -1.31
     interviewer
    -1.28
     populace
    -1.27
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.80
    Buyable
    1.70
    aturdays
    1.63
    FORMATION
    1.56
    Adventure
    1.52
    Brew
    1.50
    �
    1.48
     curated
    1.46
    DEN
    1.44
    EEK
    1.42
    Activations Density 0.070%

    No Known Activations