© 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. 2396
    Prev
    Next
    INDEX
    Explanations

    references to examples or specific instances related to topics discussed

    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
    0:0.02
    1:0.01
    2:0.29
    3:0.13
    4:0.15
    5:0.02
    6:0.05
    7:0.05
    8:0.05
    9:0.05
    10:0.07
    11:0.06
    Negative Logits
     +/-
    -1.79
    ertodd
    -1.70
    ~~~~~~~~
    -1.60
    dropping
    -1.57
    ¯¯¯¯
    -1.55
    killing
    -1.54
    minist
    -1.51
    neutral
    -1.50
    ────
    -1.49
    ¯¯
    -1.46
    POSITIVE LOGITS
    ahon
    1.67
    ype
    1.49
     Cond
    1.43
     consolidation
    1.39
    prem
    1.38
     Virt
    1.36
    lain
    1.35
    awei
    1.35
     Conrad
    1.32
    anca
    1.31
    Activations Density 0.000%

    No Known Activations