© 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. 27086
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "data"

    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
    504
    +0.14
    0.8%
    111
    +0.12
    0.6%
    28
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.14
    0.06
    246
    +0.12
    0.05
    184
    +0.11
    0.05
    Negative Logits
    arer
    -1.63
     parental
    -1.34
     maternal
    -1.33
    pherd
    -1.32
    esta
    -1.31
    sex
    -1.30
    specific
    -1.29
    encer
    -1.28
    ij
    -1.28
     remained
    -1.26
    POSITIVE LOGITS
    icum
    1.47
     ”
    1.46
    ulas
    1.45
    ifies
    1.42
    gia
    1.42
    agram
    1.42
    ”,
    1.41
     dreams
    1.37
     lupus
    1.35
    iscus
    1.34
    Activations Density 0.074%

    No Known Activations