© 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. 45844
    Prev
    Next
    INDEX
    Explanations

    high-frequency content words and phrases that signify organization or structure in text

    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
    1:0.02
    2:0.09
    3:0.06
    4:0.09
    5:0.02
    6:0.07
    7:0.35
    8:0.03
    9:0.02
    10:0.11
    11:0.07
    Negative Logits
    arcity
    -1.76
    bucks
    -1.51
    Cu
    -1.45
    iencies
    -1.44
    intage
    -1.43
    erity
    -1.43
    cold
    -1.43
    imo
    -1.42
    opol
    -1.42
    itors
    -1.37
    POSITIVE LOGITS
     outline
    2.38
     outlines
    2.07
     outlining
    1.86
    paren
    1.74
     newsp
    1.60
     encomp
    1.59
     roadmap
    1.57
     glyph
    1.53
     snipp
    1.52
     sket
    1.51
    Activations Density 0.000%

    No Known Activations