© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27911
    Prev
    Next
    INDEX
    Explanations

    hashtags related to events or topics

    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
    77
    +0.13
    0.7%
    154
    +0.11
    0.6%
    326
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.13
    0.01
    229
    +0.11
    0.01
    111
    +0.11
    0.01
    Negative Logits
    duced
    -1.55
    nd
    -1.55
    aning
    -1.44
     resulting
    -1.44
    +$
    -1.42
     transcribed
    -1.40
    ffected
    -1.38
    iginally
    -1.38
     remaining
    -1.38
     principal
    -1.36
    POSITIVE LOGITS
    bour
    1.89
    iors
    1.82
    asek
    1.74
     (@
    1.69
     violates
    1.68
    stown
    1.65
    bank
    1.61
     reminds
    1.58
    dimen
    1.58
    chitz
    1.54
    Activations Density 0.015%

    No Known Activations