© 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. 0-MLP-SM
    11. 30724
    Prev
    Next
    INDEX
    Explanations

    technical terms related to passive house standards

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    410
    +0.15
    0.8%
    364
    +0.12
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    410
    +0.12
    0.01
    330
    +0.12
    0.01
    Negative Logits
    urope
    -2.03
    eren
    -1.75
    ://
    -1.68
     e
    -1.50
    ea
    -1.48
     ou
    -1.47
     curiam
    -1.46
    ável
    -1.44
    resis
    -1.41
    zia
    -1.41
    POSITIVE LOGITS
    £
    3.45
    ¥
    2.73
    Ĵ
    2.66
    ĻĤ
    2.55
    ©
    2.54
    ĵ
    2.52
    ļ
    2.50
    ¤
    2.44
    ĺ
    2.44
    Į
    2.44
    Activations Density 0.011%

    No Known Activations