© 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. 10277
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or speech

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.05
    4:0.07
    5:0.04
    6:0.16
    7:0.04
    8:0.04
    9:0.05
    10:0.06
    11:0.32
    Negative Logits
     Illegal
    -2.02
    Posted
    -1.95
    posted
    -1.79
     Investig
    -1.78
     Detected
    -1.71
    CHAT
    -1.69
    laughter
    -1.69
    ----------
    -1.66
     Provides
    -1.63
     Reply
    -1.63
    POSITIVE LOGITS
    sbm
    1.91
     masse
    1.85
     baseline
    1.79
    letal
    1.75
    ithing
    1.73
     disposable
    1.72
     theirs
    1.70
     measuring
    1.69
    vana
    1.68
     measurement
    1.68
    Activations Density 0.003%

    No Known Activations