© 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. 782
    Prev
    Next
    INDEX
    Explanations

    references to the concept of appropriation, particularly in financial and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.08
    3:0.06
    4:0.11
    5:0.02
    6:0.04
    7:0.40
    8:0.03
    9:0.03
    10:0.09
    11:0.05
    Negative Logits
    rolog
    -1.55
    Reviewed
    -1.55
    repair
    -1.47
    lehem
    -1.44
    irmed
    -1.43
    sburgh
    -1.41
     departures
    -1.40
    confirmed
    -1.39
    psey
    -1.39
    shine
    -1.38
    POSITIVE LOGITS
     appropriated
    1.82
     borrowed
    1.74
     funds
    1.67
     Marketable
    1.64
    appropri
    1.61
     appropriation
    1.60
    ��
    1.44
    displayText
    1.44
    デ
    1.43
     Tokens
    1.43
    Activations Density 0.001%

    No Known Activations