© 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. 770
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific formatting elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.34
    1:0.05
    2:0.06
    3:0.09
    4:0.04
    5:0.10
    6:0.02
    7:0.02
    8:0.05
    9:0.06
    10:0.04
    11:0.07
    Negative Logits
     polar
    -1.89
     alloc
    -1.86
     character
    -1.80
     cod
    -1.75
     elev
    -1.74
     coerc
    -1.71
     UCS
    -1.70
     anim
    -1.70
     termin
    -1.66
     transforming
    -1.64
    POSITIVE LOGITS
    »
    2.71
    ……
    2.60
    ··
    2.50
    �
    2.32
    ................
    2.31
    .?
    2.27
    •
    2.22
     …"
    2.22
    .,"
    2.21
    _____
    2.20
    Activations Density 0.122%

    No Known Activations