© 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. 7716
    Prev
    Next
    INDEX
    Explanations

    phrases and statistics related to survey results and public opinion

    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
    1:0.03
    2:0.27
    3:0.09
    4:0.08
    5:0.03
    6:0.04
    7:0.07
    8:0.05
    9:0.05
    10:0.12
    11:0.09
    Negative Logits
    than
    -1.67
     Krypt
    -1.57
     Spac
    -1.27
     overrun
    -1.27
     impair
    -1.26
     Crush
    -1.23
     suffix
    -1.21
     Metallic
    -1.21
     Hell
    -1.21
     Psychic
    -1.21
    POSITIVE LOGITS
    allas
    1.74
    umbn
    1.63
    uden
    1.58
    ulhu
    1.58
    nesday
    1.55
    ogi
    1.52
    andum
    1.50
    odi
    1.46
    atis
    1.46
    ixt
    1.41
    Activations Density 0.001%

    No Known Activations