© 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. 9-ATT-KK
    11. 12124
    Prev
    Next
    INDEX
    Explanations

    quotes and expressions of emotional reactions and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.01
    2:0.09
    3:0.21
    4:0.04
    5:0.07
    6:0.01
    7:0.06
    8:0.03
    9:0.01
    10:0.33
    11:0.02
    Negative Logits
    rawdownloadcloneembedreportprint
    -2.14
    .>>
    -2.12
    Wikipedia
    -2.09
     Description
    -2.05
    Myth
    -2.02
    }:
    -1.98
    ](
    -1.93
    Parameters
    -1.91
    Via
    -1.90
    ?,
    -1.90
    POSITIVE LOGITS
     remorse
    2.76
     repent
    2.63
     hoped
    2.61
     sympath
    2.50
     pleased
    2.48
     regrets
    2.48
     regret
    2.44
     hope
    2.41
     consulted
    2.40
     reconsider
    2.36
    Activations Density 0.307%

    No Known Activations