© 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. 19779
    Prev
    Next
    INDEX
    Explanations

    phrases indicating positive sentiments or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.12
    3:0.08
    4:0.18
    5:0.01
    6:0.08
    7:0.29
    8:0.04
    9:0.02
    10:0.04
    11:0.06
    Negative Logits
    ancies
    -1.67
    essential
    -1.50
    opathic
    -1.45
     conson
    -1.42
     soph
    -1.42
    OME
    -1.41
    olars
    -1.40
     counterparts
    -1.38
    ses
    -1.36
    vable
    -1.30
    POSITIVE LOGITS
    ipedia
    1.63
     Revenge
    1.55
     Scope
    1.49
    risk
    1.42
     Enterprises
    1.39
     Journalists
    1.38
     Disclosure
    1.36
     Prevention
    1.36
     Protect
    1.33
    aea
    1.29
    Activations Density 0.006%

    No Known Activations