© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29234
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ard."

    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
    211
    +0.14
    0.8%
    465
    +0.12
    0.7%
    108
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    211
    +0.14
    0.04
    465
    +0.12
    0.03
    108
    +0.12
    0.03
    Negative Logits
    ?'
    -1.69
     ?"
    -1.66
     ."
    -1.55
    laid
    -1.49
    áĢº
    -1.47
    ursor
    -1.47
     regard
    -1.46
    lay
    -1.46
    acet
    -1.45
    epithelial
    -1.44
    POSITIVE LOGITS
    ificial
    1.77
    enstein
    1.76
    iom
    1.69
    ios
    1.67
    esan
    1.66
    ality
    1.64
    wolf
    1.62
    illery
    1.60
    iously
    1.59
    lessness
    1.57
    Activations Density 11.469%

    No Known Activations