© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27027
    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
    277
    +0.12
    0.7%
    361
    +0.12
    0.6%
    259
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.12
    0.12
    264
    +0.12
    0.12
    331
    +0.11
    0.10
    Negative Logits
    ents
    -1.75
    ahoma
    -1.66
     equals
    -1.51
    ppa
    -1.45
    ante
    -1.45
     accompan
    -1.44
    ente
    -1.43
    taire
    -1.43
    stown
    -1.42
    esome
    -1.39
    POSITIVE LOGITS
    ĨĴ
    2.46
    ¾
    2.15
    ¬
    2.10
    ł
    2.07
    Ļ
    2.04
    ģ
    2.04
    »
    1.94
    <|outofrange|>
    1.93
                                            
    1.93
                                           
    1.93
    Activations Density 0.137%

    No Known Activations

    This feature has no known activations.