© 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. 26973
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ABLE" and variations thereof, indicating a focus on capability or potential

    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
    417
    +0.15
    0.9%
    72
    +0.10
    0.6%
    161
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.15
    0.02
    161
    +0.10
    0.01
    66
    +0.10
    0.01
    Negative Logits
    cluded
    -1.80
     affected
    -1.72
     probable
    -1.71
     full
    -1.71
     computed
    -1.69
    nered
    -1.69
    .");
    -1.68
    ĥ½
    -1.58
     reasonable
    -1.57
     narrowed
    -1.56
    POSITIVE LOGITS
    anguage
    2.23
    inux
    2.20
    ENCE
    2.01
    emente
    2.00
    esan
    1.87
    elta
    1.79
    endas
    1.68
     feat
    1.68
    icense
    1.68
    etto
    1.67
    Activations Density 0.019%

    No Known Activations