© 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. 24334
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical treatment and research processes

    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
    159
    +0.15
    0.9%
    176
    +0.13
    0.7%
    252
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.15
    0.07
    100
    +0.13
    0.08
    2
    +0.12
    0.05
    Negative Logits
    ł
    -3.29
    ij
    -3.20
    ĸ
    -3.10
    Ĵ
    -3.04
    Ļ
    -3.00
    «
    -2.99
    £
    -2.98
    ª
    -2.97
    ī
    -2.91
    ¯
    -2.89
    POSITIVE LOGITS
    =”
    1.61
    starter
    1.60
     fundraising
    1.47
     affairs
    1.43
     practice
    1.41
    itively
    1.38
     minds
    1.38
    ters
    1.38
    itional
    1.36
     treasure
    1.33
    Activations Density 0.655%

    No Known Activations