© 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. 10073
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest strategies or methods for improvement or action

    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
    0:0.01
    1:0.02
    2:0.11
    3:0.07
    4:0.09
    5:0.02
    6:0.09
    7:0.33
    8:0.03
    9:0.02
    10:0.08
    11:0.08
    Negative Logits
     Britann
    -1.61
    areth
    -1.40
    terms
    -1.38
     alone
    -1.32
    ebook
    -1.30
     Seconds
    -1.29
     batches
    -1.29
     Monstrous
    -1.28
    seconds
    -1.28
     Awakens
    -1.28
    POSITIVE LOGITS
     workaround
    1.63
     nuisance
    1.60
    Disable
    1.46
     coping
    1.37
     misuse
    1.37
    ventions
    1.37
    Avoid
    1.35
    Better
    1.33
     disrupt
    1.33
     mimic
    1.33
    Activations Density 0.016%

    No Known Activations