© 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. 27105
    Prev
    Next
    INDEX
    Explanations

    terms related to social justice and activism

    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
    2:0.47
    3:0.05
    4:0.05
    5:0.03
    6:0.09
    7:0.02
    8:0.03
    9:0.04
    10:0.08
    11:0.04
    Negative Logits
    anwhile
    -1.66
     shrouded
    -1.55
    ousy
    -1.53
     staggering
    -1.53
    ْ
    -1.50
     compromises
    -1.50
    ruary
    -1.49
    田
    -1.45
    terness
    -1.43
     intersections
    -1.43
    POSITIVE LOGITS
     iT
    1.89
    DN
    1.82
     (@
    1.80
    blogspot
    1.70
    mc
    1.67
    @
    1.63
    QB
    1.60
    Radio
    1.59
    MN
    1.59
    eu
    1.58
    Activations Density 0.226%

    No Known Activations