© 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. 36207
    Prev
    Next
    INDEX
    Explanations

    references to websites and URLs

    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
    0:0.07
    1:0.03
    2:0.10
    3:0.03
    4:0.06
    5:0.13
    6:0.05
    7:0.04
    8:0.35
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
    76561
    -1.94
    Untitled
    -1.53
    mons
    -1.53
    ciating
    -1.49
    oby
    -1.45
     describ
    -1.41
    avan
    -1.39
    etz
    -1.37
    Roy
    -1.36
    BALL
    -1.36
    POSITIVE LOGITS
    phrine
    2.09
     DAC
    2.00
     istg
    1.80
     Delta
    1.74
     Psy
    1.71
     Astral
    1.61
     Chimera
    1.60
     successors
    1.55
     Sisters
    1.50
     Lei
    1.49
    Activations Density 0.033%

    No Known Activations