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

    Neuronpedia

    Jacobian LensNEW
    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. 11959
    Prev
    Next
    INDEX
    Explanations

    long strings of text with the word "together" repeated multiple times

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    discussions about performance and improvement in competitive settings

    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
    0:0.06
    1:0.11
    2:0.07
    3:0.03
    4:0.09
    5:0.15
    6:0.09
    7:0.07
    8:0.07
    9:0.07
    10:0.07
    11:0.06
    Negative Logits
    bill
    -1.49
     "$
    -1.41
     NPR
    -1.39
     redacted
    -1.35
    described
    -1.34
    States
    -1.34
    osponsors
    -1.34
     feds
    -1.34
     lawmakers
    -1.33
     "#
    -1.31
    POSITIVE LOGITS
     realise
    2.14
     lapt
    1.88
     manoeuv
    1.77
     streng
    1.70
    oubted
    1.66
     seiz
    1.65
     analyse
    1.63
     behaviours
    1.61
     favourable
    1.61
     secondly
    1.60
    Activations Density 0.356%

    No Known Activations