© 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 · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23650
    Prev
    Next
    INDEX
    Explanations

    terms related to therapeutic applications in medicine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    150
    +0.19
    1.1%
    160
    +0.15
    0.8%
    14
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.19
    0.02
    150
    +0.15
    0.01
    14
    +0.12
    0.02
    Negative Logits
    Ń
    -3.59
    ŀ
    -3.57
    ħ
    -3.36
    §
    -3.32
    ķ
    -3.25
    ij
    -3.24
    »
    -3.21
    ©
    -3.18
    ł
    -3.16
    Ĺ
    -3.13
    POSITIVE LOGITS
    esian
    1.93
    namese
    1.62
    Å¡ÃŃ
    1.57
    ibase
    1.52
    aurus
    1.51
    rifug
    1.50
    icolor
    1.49
    ses
    1.45
    amais
    1.43
    etter
    1.38
    Activations Density 0.156%

    No Known Activations