© 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. 26824
    Prev
    Next
    INDEX
    Explanations

    terms related to legal obligations and restrictions

    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
    376
    +0.18
    1.0%
    184
    +0.12
    0.7%
    463
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.18
    0.02
    463
    +0.12
    0.02
    317
    +0.12
    0.02
    Negative Logits
    ubicin
    -1.99
    woke
    -1.71
    ctomy
    -1.51
     preponderance
    -1.49
     Cauc
    -1.47
    ocytes
    -1.39
     diagnosed
    -1.38
     AIDS
    -1.36
    ce
    -1.28
    AML
    -1.28
    POSITIVE LOGITS
    .";
    1.63
     ones
    1.59
     favorites
    1.58
    imensional
    1.56
    ';
    1.55
    iment
    1.55
     styles
    1.52
     aren
    1.51
     deadlines
    1.50
    iencies
    1.50
    Activations Density 0.026%

    No Known Activations