© 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. 27098
    Prev
    Next
    INDEX
    Explanations

    references to the Federal Reserve

    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
    141
    +0.17
    1.0%
    44
    +0.14
    0.8%
    100
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.17
    0.01
    70
    +0.14
    0.01
    85
    +0.10
    0.01
    Negative Logits
    lasses
    -1.58
     fair
    -1.55
     merry
    -1.43
    amais
    -1.42
     merc
    -1.40
    '?"
    -1.40
    |$.
    -1.38
    '>
    -1.38
     sess
    -1.37
    hab
    -1.37
    POSITIVE LOGITS
    icum
    2.06
    erd
    1.92
    bank
    1.84
    etable
    1.66
    ilee
    1.63
    craft
    1.60
    fecture
    1.59
    forge
    1.59
    IPE
    1.58
    encial
    1.56
    Activations Density 0.432%

    No Known Activations