© 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. 44002
    Prev
    Next
    INDEX
    Explanations

    expressions and instances related to hate speech and its consequences

    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
    0:0.01
    1:0.01
    2:0.09
    3:0.05
    4:0.05
    5:0.03
    6:0.33
    7:0.06
    8:0.03
    9:0.03
    10:0.17
    11:0.09
    Negative Logits
    将
    -1.46
    */(
    -1.43
    生
    -1.42
    pole
    -1.31
    NEY
    -1.28
     baseman
    -1.28
    版
    -1.28
    ESA
    -1.26
    itte
    -1.24
    aple
    -1.24
    POSITIVE LOGITS
     intimidation
    1.47
     terrorism
    1.31
    itives
    1.21
    hate
    1.20
     terror
    1.19
    upload
    1.17
    illance
    1.16
     Cthulhu
    1.16
     vandalism
    1.16
     bullying
    1.15
    Activations Density 0.005%

    No Known Activations