© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 43926
    Prev
    Next
    INDEX
    Explanations

    expressions related to cultural or ethnic identity

    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
    0:0.03
    1:0.02
    2:0.07
    3:0.05
    4:0.04
    5:0.04
    6:0.45
    7:0.04
    8:0.03
    9:0.06
    10:0.07
    11:0.05
    Negative Logits
    -+-+
    -1.49
    NECT
    -1.31
     pse
    -1.23
     vigilance
    -1.20
    olesterol
    -1.18
    ICAN
    -1.16
    ATING
    -1.14
    vertisements
    -1.14
    Services
    -1.13
    estic
    -1.13
    POSITIVE LOGITS
    �
    1.75
     Rebels
    1.36
    bye
    1.35
    rette
    1.28
    ghan
    1.25
    emp
    1.20
     forgiven
    1.18
    quez
    1.17
    undle
    1.15
    ndra
    1.15
    Activations Density 0.001%

    No Known Activations