© 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. 26278
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    427
    +0.14
    0.7%
    129
    +0.13
    0.7%
    127
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.14
    0.04
    81
    +0.13
    0.03
    471
    +0.11
    0.02
    Negative Logits
     deviations
    -1.50
    ses
    -1.50
     conduc
    -1.48
     cancell
    -1.43
     cry
    -1.39
     whatsoever
    -1.39
     insu
    -1.38
     enough
    -1.37
     circumstances
    -1.37
     worn
    -1.36
    POSITIVE LOGITS
    erl
    2.06
    orean
    1.64
    ļ
    1.60
    minute
    1.55
    eca
    1.54
    reek
    1.51
    mozilla
    1.49
    ĸ
    1.48
    PHP
    1.45
    street
    1.43
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.