© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 41456
    Prev
    Next
    INDEX
    Explanations

    punctuation symbols, particularly commas

    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
    0:0.13
    1:0.29
    2:0.04
    3:0.03
    4:0.04
    5:0.16
    6:0.03
    7:0.02
    8:0.07
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    ソ
    -1.81
    sid
    -1.70
    覚醒
    -1.65
    MAX
    -1.49
    �
    -1.48
     Fas
    -1.42
    lymp
    -1.40
    Nap
    -1.40
    �
    -1.39
    �
    -1.38
    POSITIVE LOGITS
    ebin
    1.72
     Logged
    1.70
    owitz
    1.53
    ede
    1.46
    orians
    1.42
    alde
    1.41
    Jenn
    1.38
    ords
    1.32
    llah
    1.32
    rogram
    1.30
    Activations Density 0.013%

    No Known Activations