© 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. 41503
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks, with an emphasis on their frequency and placement

    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
    0:0.03
    1:0.03
    2:0.05
    3:0.06
    4:0.04
    5:0.05
    6:0.39
    7:0.03
    8:0.04
    9:0.06
    10:0.07
    11:0.07
    Negative Logits
    HAHAHAHA
    -1.47
     funn
    -1.40
    VALUE
    -1.31
    ONSORED
    -1.30
    ELF
    -1.23
     cov
    -1.19
    QL
    -1.15
     misdem
    -1.14
    xtap
    -1.12
     coinc
    -1.11
    POSITIVE LOGITS
    heit
    1.78
    rency
    1.59
    forth
    1.59
    wine
    1.55
    fried
    1.51
    nir
    1.46
    ë
    1.45
    tsky
    1.44
    enment
    1.43
    hess
    1.43
    Activations Density 0.003%

    No Known Activations