© 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 EvalsExportsinterp-engineNEWAPI 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. 26388
    Prev
    Next
    INDEX
    Explanations

    the phrase "Top 10" and similar rankings in the text

    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
    156
    +0.16
    0.9%
    376
    +0.13
    0.7%
    305
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    305
    +0.16
    0.02
    78
    +0.13
    0.01
    279
    +0.12
    0.01
    Negative Logits
     cool
    -1.59
     hereby
    -1.59
    matically
    -1.57
     WARRANTIES
    -1.51
     permission
    -1.49
    ANCE
    -1.47
    uting
    -1.45
    ness
    -1.42
    '?"
    -1.42
     yours
    -1.42
    POSITIVE LOGITS
    phal
    1.62
    het
    1.61
    Street
    1.56
    ÃŃf
    1.53
    ologies
    1.51
    real
    1.51
    MV
    1.46
    strand
    1.41
     dollar
    1.40
    stone
    1.39
    Activations Density 0.010%

    No Known Activations