© 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. 5-ATT-KK
    11. 44944
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators in the text

    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
    0:0.17
    1:0.34
    2:0.02
    3:0.03
    4:0.02
    5:0.09
    6:0.03
    7:0.02
    8:0.07
    9:0.08
    10:0.04
    11:0.03
    Negative Logits
    onite
    -1.99
    ppa
    -1.91
     eleph
    -1.84
    inet
    -1.82
    enable
    -1.63
    bably
    -1.58
     dotted
    -1.57
    pez
    -1.57
    fix
    -1.55
     wed
    -1.55
    POSITIVE LOGITS
     The
    2.37
     Transactions
    2.06
     Voices
    2.00
     Views
    1.94
     Colors
    1.91
     Thought
    1.88
     Sett
    1.88
     Factors
    1.87
     Dimensions
    1.86
     Settlement
    1.83
    Activations Density 0.022%

    No Known Activations