© 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. 38350
    Prev
    Next
    INDEX
    Explanations

    phrases and conjunctions that indicate reasoning or causation

    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
    0:0.18
    1:0.06
    2:0.06
    3:0.05
    4:0.06
    5:0.09
    6:0.03
    7:0.05
    8:0.13
    9:0.05
    10:0.07
    11:0.11
    Negative Logits
     lesbian
    -1.81
     analytic
    -1.62
    rite
    -1.56
    ..."
    -1.50
     resent
    -1.47
     hate
    -1.42
     homosexual
    -1.41
     masters
    -1.40
     Kindle
    -1.40
     mistress
    -1.40
    POSITIVE LOGITS
    interstitial
    1.82
    achus
    1.79
    lasses
    1.76
    clips
    1.75
    yards
    1.74
    oval
    1.71
    hoe
    1.70
    uch
    1.63
    �
    1.58
    cffff
    1.54
    Activations Density 0.000%

    No Known Activations