© 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. 5-ATT-KK
    11. 43468
    Prev
    Next
    INDEX
    Explanations

    concepts related to statistics and numerical comparisons

    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
    0:0.15
    1:0.24
    2:0.03
    3:0.05
    4:0.02
    5:0.16
    6:0.03
    7:0.01
    8:0.11
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
    410
    -1.69
    standing
    -1.66
    540
    -1.66
    stood
    -1.65
    770
    -1.63
    660
    -1.58
    380
    -1.53
    530
    -1.52
    940
    -1.50
    {"
    -1.50
    POSITIVE LOGITS
     vs
    2.52
     =================
    2.12
     VS
    2.11
     Vs
    2.08
     ->
    2.06
    ……………………
    1.79
     Killed
    1.79
     -=
    1.78
    的
    1.74
     Versus
    1.72
    Activations Density 0.004%

    No Known Activations