© 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. 37144
    Prev
    Next
    INDEX
    Explanations

    punctuation or formatting marks in a 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
    0:0.09
    1:0.05
    2:0.19
    3:0.05
    4:0.04
    5:0.02
    6:0.07
    7:0.08
    8:0.10
    9:0.02
    10:0.12
    11:0.11
    Negative Logits
    assetsadobe
    -1.91
    nih
    -1.83
    nces
    -1.83
    sterdam
    -1.76
    ulas
    -1.73
    76561
    -1.71
     Samar
    -1.69
    obos
    -1.69
    lik
    -1.66
     ABE
    -1.66
    POSITIVE LOGITS
     antioxid
    1.63
     climax
    1.57
     responsive
    1.52
     uninterrupted
    1.51
     bounce
    1.50
    ————
    1.49
    Voice
    1.46
     uncom
    1.45
     emph
    1.45
     finish
    1.45
    Activations Density 0.000%

    No Known Activations