© 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. 25534
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "progressive" or related terms indicating progressive ideas or policies

    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
    +0.26
    1.5%
    125
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.26
    0.01
    339
    +0.13
    0.01
    48
    +0.12
    0.01
    Negative Logits
    rocy
    -1.64
    ĥ½
    -1.63
    ori
    -1.50
     particular
    -1.47
     cruel
    -1.44
     Marathon
    -1.35
    ights
    -1.32
    érie
    -1.32
    ene
    -1.31
    rae
    -1.28
    POSITIVE LOGITS
     streak
    1.69
    "}](#
    1.65
    {}{
    1.58
    thirds
    1.52
    ulence
    1.51
    ulum
    1.45
    wise
    1.45
    ulent
    1.44
    ism
    1.44
    casting
    1.41
    Activations Density 0.015%

    No Known Activations