© 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. 44945
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements that indicate dialogue or quotations

    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
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.05
    5:0.03
    6:0.21
    7:0.26
    8:0.06
    9:0.03
    10:0.11
    11:0.07
    Negative Logits
    thood
    -1.97
    yip
    -1.73
     secondly
    -1.64
    iqueness
    -1.51
    Sov
    -1.43
     wip
    -1.41
    hift
    -1.39
    soever
    -1.39
    esson
    -1.38
    ️
    -1.36
    POSITIVE LOGITS
     Milwaukee
    1.52
     Indianapolis
    1.50
     Webster
    1.46
     Middles
    1.45
    dest
    1.42
     southwestern
    1.40
    library
    1.38
    ヴァ
    1.38
    BUR
    1.38
    termin
    1.38
    Activations Density 0.008%

    No Known Activations