© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28662
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols indicating structure or organization in 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
    0:0.03
    1:0.01
    2:0.14
    3:0.12
    4:0.08
    5:0.03
    6:0.03
    7:0.28
    8:0.06
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
    ancies
    -1.73
     labels
    -1.67
     thresholds
    -1.57
     faults
    -1.47
    older
    -1.45
    RANT
    -1.44
    aults
    -1.41
     taboo
    -1.41
     deems
    -1.37
    errors
    -1.37
    POSITIVE LOGITS
    _____
    1.52
    isin
    1.41
    itte
    1.41
    ◼
    1.41
     evangel
    1.39
     overcoming
    1.38
    anooga
    1.38
    ¯¯¯¯¯¯¯¯
    1.35
    escape
    1.33
    incent
    1.32
    Activations Density 0.015%

    No Known Activations