© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 34314
    Prev
    Next
    INDEX
    Explanations

    references to food and dietary habits

    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
    1:0.01
    2:0.21
    3:0.08
    4:0.11
    5:0.03
    6:0.04
    7:0.07
    8:0.04
    9:0.04
    10:0.14
    11:0.13
    Negative Logits
    senal
    -1.83
    ocus
    -1.55
     Hutchinson
    -1.39
    icent
    -1.36
    ORY
    -1.32
    onomy
    -1.31
     causation
    -1.25
     pragmatic
    -1.22
    ior
    -1.21
     insur
    -1.20
    POSITIVE LOGITS
    laughter
    1.63
    instead
    1.52
    daily
    1.43
     instead
    1.39
    berries
    1.38
    without
    1.33
    during
    1.31
     while
    1.28
    eln
    1.27
     Allaah
    1.27
    Activations Density 0.049%

    No Known Activations