© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 12492
    Prev
    Next
    INDEX
    Explanations

    references to specific formats or structures, like citations and formatting instructions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to giving or offering assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.3.attn.hook_z
    Hook Layer
    3
    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
    1:0.11
    2:0.07
    3:0.05
    4:0.04
    5:0.14
    6:0.09
    7:0.10
    8:0.07
    9:0.07
    10:0.09
    11:0.07
    Negative Logits
    xit
    -1.92
    zbollah
    -1.76
    hedon
    -1.71
    geist
    -1.68
     Learns
    -1.66
    thood
    -1.55
    xual
    -1.54
    ndum
    -1.52
     Ruin
    -1.50
    milo
    -1.46
    POSITIVE LOGITS
     catalog
    1.65
     publication
    1.60
     domain
    1.46
     domains
    1.41
     transcription
    1.38
     databases
    1.37
     statistical
    1.33
     publishers
    1.33
     publications
    1.32
     dot
    1.30
    Activations Density 0.000%

    No Known Activations