© 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. 19663
    Prev
    Next
    INDEX
    Explanations

    URLs from social media platforms, particularly Twitter

    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
    0:0.16
    1:0.27
    2:0.04
    3:0.05
    4:0.08
    5:0.02
    6:0.05
    7:0.05
    8:0.01
    9:0.06
    10:0.04
    11:0.08
    Negative Logits
     GOODMAN
    -1.73
    idate
    -1.70
    tackle
    -1.69
    represented
    -1.65
    lins
    -1.64
    indal
    -1.58
    channelAvailability
    -1.51
    metics
    -1.51
    footed
    -1.49
    attery
    -1.39
    POSITIVE LOGITS
    /-
    1.83
    /(
    1.61
    /
    1.58
     Doc
    1.46
     tighter
    1.45
    uary
    1.41
     cess
    1.40
     autop
    1.31
     undo
    1.29
     nep
    1.28
    Activations Density 0.005%

    No Known Activations