© 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. 27940
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there."

    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
    375
    +0.13
    0.7%
    40
    +0.11
    0.6%
    59
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.13
    0.17
    278
    +0.11
    0.17
    114
    +0.10
    0.12
    Negative Logits
    abled
    -1.63
     fewer
    -1.59
    '?"
    -1.52
    ,''
    -1.51
    "?"
    -1.45
    amps
    -1.44
    eric
    -1.43
    "--
    -1.42
    msgstr
    -1.42
     Wrote
    -1.41
    POSITIVE LOGITS
    holding
    1.65
    fal
    1.45
    SUCCESS
    1.39
    PING
    1.39
    pping
    1.38
    front
    1.34
    uri
    1.32
    filling
    1.31
    holder
    1.31
     disposable
    1.30
    Activations Density 0.549%

    No Known Activations