© 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. 39493
    Prev
    Next
    INDEX
    Explanations

    various types of qualitative assessments and comparisons in public discourse

    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
    0:0.02
    1:0.02
    2:0.19
    3:0.14
    4:0.23
    5:0.02
    6:0.09
    7:0.06
    8:0.06
    9:0.02
    10:0.05
    11:0.05
    Negative Logits
     neutrality
    -1.54
    ————————
    -1.39
    IDES
    -1.39
    icio
    -1.32
    MSN
    -1.29
    eware
    -1.27
    avascript
    -1.26
    arat
    -1.26
    ?????
    -1.25
     exclus
    -1.24
    POSITIVE LOGITS
    sect
    1.58
    stellar
    1.46
    ueller
    1.38
    ¯
    1.35
    aptic
    1.34
     contexts
    1.24
     brewer
    1.23
     foreseeable
    1.20
     persuasion
    1.18
    eele
    1.18
    Activations Density 0.014%

    No Known Activations