© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 28871
    Prev
    Next
    INDEX
    Explanations

    references to medical professions and credentials

    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
    2:0.09
    3:0.08
    4:0.12
    5:0.04
    6:0.07
    7:0.04
    8:0.15
    9:0.05
    10:0.13
    11:0.14
    Negative Logits
    Adds
    -1.32
     Bosh
    -1.22
     Hok
    -1.19
    chet
    -1.16
     resistance
    -1.12
     unbeat
    -1.11
     Mask
    -1.10
     Statue
    -1.10
     Coil
    -1.09
     emanc
    -1.08
    POSITIVE LOGITS
    ateur
    1.31
    alys
    1.18
    BLIC
    1.18
    details
    1.17
    riter
    1.16
    prise
    1.15
    ISO
    1.14
     "$:/
    1.14
     roundup
    1.14
    aceae
    1.13
    Activations Density 0.001%

    No Known Activations