© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    references to people or person-related topics

    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
    156
    +0.18
    1.1%
    376
    +0.18
    1.0%
    34
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.18
    0.02
    3
    +0.18
    0.01
    18
    +0.15
    0.01
    Negative Logits
     its
    -1.61
    poons
    -1.49
     others
    -1.49
    ientos
    -1.43
     mornings
    -1.41
     adults
    -1.40
     thee
    -1.39
    iber
    -1.39
     shore
    -1.39
     our
    -1.39
    POSITIVE LOGITS
    nel
    2.51
    's
    1.84
    ality
    1.72
    nie
    1.71
    finder
    1.68
    gre
    1.65
    agment
    1.64
    isters
    1.63
    nal
    1.62
    het
    1.62
    Activations Density 0.016%

    No Known Activations