© 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. 28152
    Prev
    Next
    INDEX
    Explanations

    instances of "wonder" or "fantastic" in various contexts

    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
    259
    +0.13
    0.7%
    200
    +0.13
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.13
    0.01
    200
    +0.13
    0.01
    450
    +0.12
    0.01
    Negative Logits
    Į
    -1.68
    ITED
    -1.63
     quo
    -1.60
     ALL
    -1.58
     themselves
    -1.57
    LLOW
    -1.49
    FLAGS
    -1.46
     herself
    -1.46
    eeper
    -1.45
     wont
    -1.43
    POSITIVE LOGITS
    nement
    1.63
    bank
    1.62
    lane
    1.61
    judicial
    1.57
    bod
    1.57
    ivel
    1.55
    bes
    1.54
    beg
    1.51
    intage
    1.49
    ais
    1.46
    Activations Density 0.015%

    No Known Activations