© 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. 3208
    Prev
    Next
    INDEX
    Explanations

    terms related to social and political issues impacting marginalized communities

    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
    0:0.02
    1:0.02
    2:0.07
    3:0.20
    4:0.11
    5:0.04
    6:0.03
    7:0.05
    8:0.06
    9:0.12
    10:0.13
    11:0.07
    Negative Logits
    esty
    -1.54
    orget
    -1.33
     [+
    -1.31
    eneg
    -1.25
     glim
    -1.21
    epad
    -1.19
    NRS
    -1.16
    appropriately
    -1.15
    gow
    -1.11
    itaire
    -1.11
    POSITIVE LOGITS
    .).
    1.80
    )).
    1.69
    ).[
    1.64
    ]).
    1.60
    zinski
    1.49
     respectively
    1.41
    ?).
    1.41
     Slav
    1.34
     Vald
    1.32
    武
    1.28
    Activations Density 1.207%

    No Known Activations