© 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. 26656
    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
    334
    +0.15
    0.8%
    433
    +0.12
    0.6%
    16
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.15
    0.10
    471
    +0.12
    0.08
    66
    +0.12
    0.09
    Negative Logits
    \'
    -1.61
    alled
    -1.61
    TTP
    -1.58
    aho
    -1.47
    ja
    -1.43
    owa
    -1.37
    gated
    -1.35
    ATP
    -1.32
    hots
    -1.32
    include
    -1.30
    POSITIVE LOGITS
    ↵↵
    1.88
    1.88
    ↵↵
    1.88
    1.88
     ↵
    1.88
    1.88
    ↵
    1.88
    ↵↵
    1.88
    ↵
    1.88
    1.88
    Activations Density 0.120%

    No Known Activations

    This feature has no known activations.