© 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. 3122
    Prev
    Next
    INDEX
    Explanations

    parentheses in the 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
    1:0.02
    2:0.19
    3:0.05
    4:0.06
    5:0.03
    6:0.04
    7:0.16
    8:0.04
    9:0.04
    10:0.11
    11:0.18
    Negative Logits
    astered
    -1.92
    alon
    -1.73
    hyde
    -1.63
    ogun
    -1.60
    olics
    -1.58
    joy
    -1.57
    itia
    -1.56
    hner
    -1.53
    livion
    -1.52
    bern
    -1.50
    POSITIVE LOGITS
    ACTION
    1.72
    rab
    1.71
    Fighting
    1.65
    Range
    1.59
    urnal
    1.59
    Poké
    1.56
    href
    1.54
     ambush
    1.53
    Brave
    1.52
    Hidden
    1.50
    Activations Density 0.001%

    No Known Activations