© 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. 43380
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and norms

    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
    0:0.02
    1:0.02
    2:0.11
    3:0.13
    4:0.06
    5:0.03
    6:0.05
    7:0.03
    8:0.27
    9:0.11
    10:0.08
    11:0.04
    Negative Logits
     Schne
    -1.65
     Jagu
    -1.57
     Unch
    -1.57
     Haas
    -1.52
    FTWARE
    -1.51
    ADRA
    -1.49
     Hond
    -1.48
     succession
    -1.44
     Jere
    -1.44
     jarring
    -1.43
    POSITIVE LOGITS
    0010
    2.07
    cms
    2.06
    english
    2.03
    Reviewer
    1.92
    vor
    1.77
     サーティワン
    1.77
    odi
    1.75
    nr
    1.72
    rw
    1.69
    widget
    1.68
    Activations Density 0.103%

    No Known Activations