© 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 EvalsExportsinterp-engineNEWAPI 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. 29949
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "d"

    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
    182
    +0.12
    0.7%
    142
    +0.10
    0.6%
    132
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.12
    0.06
    128
    +0.10
    0.05
    142
    +0.09
    0.05
    Negative Logits
    lder
    -1.63
     error
    -1.60
    acial
    -1.54
    atics
    -1.43
    ffected
    -1.42
    tip
    -1.41
     cens
    -1.39
     mean
    -1.37
    -1.37
    -1.35
    POSITIVE LOGITS
    ific
    1.77
    ividual
    1.72
    ibles
    1.72
    orship
    1.66
    urable
    1.63
    ļ
    1.62
    ossier
    1.49
    enton
    1.49
    ibil
    1.49
    umber
    1.47
    Activations Density 1.378%

    No Known Activations