Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 1-ATT-KK
    6. 6285
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroscience, specifically focusing on brain regions, neural networks, and brain functions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    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
    1:0.04
    2:0.02
    3:0.01
    4:0.05
    5:0.25
    6:0.16
    7:0.08
    8:0.03
    9:0.05
    10:0.02
    11:0.15
    Negative Logits
    uld
    -1.74
    BuyableInstoreAndOnline
    -1.62
    ulas
    -1.58
    Downloadha
    -1.51
    Introduced
    -1.51
     closures
    -1.47
    alties
    -1.41
    issions
    -1.40
    ulent
    -1.39
     cents
    -1.37
    POSITIVE LOGITS
     Detect
    1.60
    Reading
    1.51
    SIGN
    1.50
     matrix
    1.48
     schizophrenia
    1.46
     reading
    1.45
     therapy
    1.41
     resonance
    1.40
     therapist
    1.40
     Exercise
    1.39
    Activations Density 0.116%

    No Known Activations