© 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. 27915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Can."

    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
    28
    +0.12
    0.7%
    376
    +0.12
    0.7%
    173
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.12
    0.03
    383
    +0.12
    0.02
    411
    +0.11
    0.02
    Negative Logits
    ARK
    -1.82
    ection
    -1.56
    Ľ
    -1.43
    ANC
    -1.43
     tracks
    -1.42
    ETHOD
    -1.41
    essen
    -1.36
    ees
    -1.34
    ennes
    -1.33
    paring
    -1.32
    POSITIVE LOGITS
    onical
    1.84
    vas
    1.67
    zon
    1.65
    terbury
    1.63
    cels
    1.56
    't
    1.48
    bian
    1.47
    zier
    1.47
     diagram
    1.46
    etti
    1.44
    Activations Density 0.368%

    No Known Activations