© 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. 3-ATT-KK
    11. 10745
    Prev
    Next
    INDEX
    Explanations

    instances of negativity or negative connotations in the context of social interactions or mental states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.08
    2:0.06
    3:0.03
    4:0.13
    5:0.13
    6:0.09
    7:0.08
    8:0.05
    9:0.05
    10:0.10
    11:0.06
    Negative Logits
     Malays
    -1.32
     licence
    -1.28
     renamed
    -1.23
    nes
    -1.22
    ARS
    -1.21
     variants
    -1.15
    Update
    -1.15
     Les
    -1.14
     USSR
    -1.14
     defunct
    -1.13
    POSITIVE LOGITS
    emonic
    1.60
    xiety
    1.40
    cknow
    1.38
    amara
    1.35
     empath
    1.33
     soothing
    1.31
    ��
    1.27
    ileged
    1.26
     nurturing
    1.26
     Volunte
    1.23
    Activations Density 0.419%

    No Known Activations