© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29095
    Prev
    Next
    INDEX
    Explanations

    the year 1995

    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
    188
    +0.11
    0.6%
    406
    +0.10
    0.6%
    113
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.11
    0.01
    132
    +0.10
    0.01
    128
    +0.10
    0.01
    Negative Logits
    ¡
    -2.25
    ŀ
    -2.22
    ´
    -2.15
    µ
    -2.10
    °
    -2.06
    ĥ
    -2.05
    ±
    -2.02
    Īĺ
    -1.99
    ½
    -1.94
    ¦
    -1.93
    POSITIVE LOGITS
     limiting
    1.56
    icing
    1.56
    arians
    1.45
    unts
    1.45
    orems
    1.42
    aire
    1.42
    eu
    1.41
    aries
    1.41
     nonsense
    1.36
    ete
    1.36
    Activations Density 0.000%

    No Known Activations