© 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. 3-ATT-KK
    11. 14467
    Prev
    Next
    INDEX
    Explanations

    political terms and events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases indicating potential failure or challenges in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.03
    1:0.06
    2:0.07
    3:0.03
    4:0.03
    5:0.10
    6:0.06
    7:0.04
    8:0.07
    9:0.35
    10:0.05
    11:0.07
    Negative Logits
    abilia
    -1.80
    Penn
    -1.63
     Cosponsors
    -1.61
    Bir
    -1.59
    Cruz
    -1.55
    Tickets
    -1.53
    Liter
    -1.53
    Cub
    -1.52
    Portland
    -1.51
    Ohio
    -1.50
    POSITIVE LOGITS
     mistaken
    1.59
    ?",
    1.51
    ointed
    1.42
     prophetic
    1.41
     luck
    1.40
     prophet
    1.38
    ?:
    1.36
     democratically
    1.35
     coincidence
    1.34
     Had
    1.33
    Activations Density 0.007%

    No Known Activations