© 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. 14289
    Prev
    Next
    INDEX
    Explanations

    references to horror movies and related descriptions

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

    references to horror films and their elements

    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
    1:0.02
    2:0.05
    3:0.19
    4:0.02
    5:0.04
    6:0.11
    7:0.25
    8:0.04
    9:0.02
    10:0.06
    11:0.11
    Negative Logits
     trustworthy
    -1.51
     guarant
    -1.49
    verning
    -1.43
     ratified
    -1.33
    ortium
    -1.28
    igham
    -1.25
     tentative
    -1.25
     trusted
    -1.19
     tolerance
    -1.14
     spons
    -1.14
    POSITIVE LOGITS
    ��
    1.86
    ��
    1.47
    plot
    1.39
    genre
    1.36
    movie
    1.30
     horror
    1.25
    ovie
    1.24
     thriller
    1.23
    owl
    1.21
    tones
    1.21
    Activations Density 0.013%

    No Known Activations