© 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. 27871
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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
    23
    +0.26
    1.4%
    300
    +0.12
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    106
    +0.26
    0.02
    0
    +0.12
    0.01
    258
    +0.12
    0.01
    Negative Logits
    emis
    -1.57
    ist
    -1.56
    ings
    -1.55
    icul
    -1.55
    ikan
    -1.55
    igraph
    -1.54
    works
    -1.52
     Azerba
    -1.50
    aci
    -1.50
     thereof
    -1.49
    POSITIVE LOGITS
     dilated
    1.79
     luck
    1.62
     innocence
    1.59
     sound
    1.53
    rying
    1.43
     smile
    1.42
     fairness
    1.40
    using
    1.39
    ensive
    1.38
     lack
    1.38
    Activations Density 0.018%

    No Known Activations