© 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 EvalsExportsAPI 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. 24691
    Prev
    Next
    INDEX
    Explanations

    references to various forms of classification or categorization

    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
    156
    +0.30
    1.8%
    23
    +0.14
    0.8%
    199
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.30
    0.09
    462
    +0.14
    0.02
    218
    +0.13
    0.06
    Negative Logits
    arynge
    -2.04
    ipart
    -1.64
    ysis
    -1.57
    ÃŃa
    -1.56
    fficients
    -1.50
    isson
    -1.49
    ésident
    -1.48
    io
    -1.48
    ost
    -1.48
    iop
    -1.47
    POSITIVE LOGITS
    lay
    1.43
     separate
    1.40
    cribing
    1.36
     ste
    1.36
     dealing
    1.36
    horse
    1.34
     competitors
    1.34
     pets
    1.32
     food
    1.32
     cold
    1.31
    Activations Density 1.695%

    No Known Activations