© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 40794
    Prev
    Next
    INDEX
    Explanations

    instances of historical or political comparisons related to oppression and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.11
    3:0.19
    4:0.24
    5:0.03
    6:0.02
    7:0.06
    8:0.07
    9:0.04
    10:0.08
    11:0.06
    Negative Logits
    perse
    -1.61
    cture
    -1.53
    hyde
    -1.52
    asive
    -1.49
    sbm
    -1.47
    phasis
    -1.46
     Became
    -1.45
    ENSE
    -1.42
     <-
    -1.42
    bishop
    -1.41
    POSITIVE LOGITS
    verty
    1.73
     predecessors
    1.65
     iceberg
    1.64
     precedent
    1.59
     counterparts
    1.59
     alternatives
    1.56
     predecessor
    1.50
     Hol
    1.46
     Nazis
    1.46
     equivalents
    1.46
    Activations Density 0.025%

    No Known Activations