© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28020
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    477
    +0.12
    0.7%
    278
    +0.12
    0.7%
    239
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    506
    +0.12
    0.07
    124
    +0.12
    0.07
    36
    +0.12
    0.07
    Negative Logits
    omitempty
    -1.78
    ment
    -1.74
    here
    -1.62
    yp
    -1.61
    their
    -1.60
    acters
    -1.53
    onto
    -1.53
    avirus
    -1.50
    ter
    -1.49
    ---|---
    -1.49
    POSITIVE LOGITS
     offices
    1.61
     approval
    1.56
     office
    1.56
     pipeline
    1.54
     staging
    1.47
     802
    1.47
    borg
    1.45
     appro
    1.45
     assistance
    1.44
     aid
    1.42
    Activations Density 0.210%

    No Known Activations