© 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. 42946
    Prev
    Next
    INDEX
    Explanations

    words related to microcephaly and its associated medical context

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.04
    5:0.04
    6:0.43
    7:0.05
    8:0.06
    9:0.05
    10:0.06
    11:0.05
    Negative Logits
    ベ
    -1.46
    SPONSORED
    -1.23
    idays
    -1.19
     SB
    -1.16
    resa
    -1.16
    Daily
    -1.15
    inav
    -1.13
    VG
    -1.12
    atform
    -1.11
     misconceptions
    -1.09
    POSITIVE LOGITS
    aign
    1.45
    ionage
    1.31
    illion
    1.30
    rouse
    1.30
    ophys
    1.29
    ortium
    1.28
    EStream
    1.28
    ּ
    1.28
    vez
    1.27
    Interstitial
    1.27
    Activations Density 0.003%

    No Known Activations