© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 44957
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral philosophy and different forms of political ideologies

    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
    0:0.08
    1:0.12
    2:0.02
    3:0.02
    4:0.02
    5:0.36
    6:0.03
    7:0.02
    8:0.04
    9:0.08
    10:0.10
    11:0.05
    Negative Logits
     Goose
    -1.82
     Skip
    -1.78
    anwhile
    -1.77
    20439
    -1.72
    tained
    -1.60
    �
    -1.59
     sqor
    -1.59
    CLASSIFIED
    -1.58
     retri
    -1.55
     clipping
    -1.55
    POSITIVE LOGITS
    etics
    2.63
    ists
    2.48
     theorists
    2.23
    ist
    2.14
    ism
    2.06
     philosophy
    2.04
    ionics
    2.02
     philosophies
    2.01
    iculture
    1.98
    etic
    1.97
    Activations Density 0.113%

    No Known Activations