© 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. 2-MLP-SM
    11. 26712
    Prev
    Next
    INDEX
    Explanations

    references to formal statements and documentation structure

    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
    500
    +0.13
    0.7%
    111
    +0.10
    0.6%
    423
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.13
    0.01
    283
    +0.10
    0.03
    410
    +0.10
    0.01
    Negative Logits
    ationally
    -1.75
    naments
    -1.63
    ata
    -1.52
    uality
    -1.50
    ifications
    -1.48
    ttp
    -1.47
    ctors
    -1.46
    EST
    -1.43
    places
    -1.41
    ums
    -1.40
    POSITIVE LOGITS
    ®
    1.95
     ↵
    1.94
    1.94
     ↵
    1.94
    1.94
    ↵
    1.94
    ↵
    1.94
    ↵
    1.94
    <|outofrange|>
    1.94
    ↵
    1.94
    Activations Density 0.267%

    No Known Activations