© 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. 27025
    Prev
    Next
    INDEX
    Explanations

    references to the substance "thorium" or related concepts 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
    71
    +0.13
    0.7%
    111
    +0.12
    0.7%
    182
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    182
    +0.12
    0.01
    71
    +0.11
    0.01
    Negative Logits
     value
    -1.49
    iginally
    -1.44
     Isle
    -1.38
     inventors
    -1.36
     supra
    -1.36
     potential
    -1.35
     ours
    -1.35
     enter
    -1.34
    ery
    -1.31
    hern
    -1.28
    POSITIVE LOGITS
    ¼
    1.72
    assic
    1.70
    acic
    1.66
    º
    1.66
    ī
    1.63
    ĻĤ
    1.63
    oque
    1.63
    aho
    1.62
    ģ
    1.59
    ³
    1.57
    Activations Density 0.004%

    No Known Activations