© 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. 25899
    Prev
    Next
    INDEX
    Explanations

    references to software and legal disclaimers related to liability

    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
    376
    +0.15
    0.9%
    412
    +0.10
    0.6%
    156
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.15
    0.01
    318
    +0.10
    0.01
    432
    +0.10
    0.01
    Negative Logits
     grateful
    -1.47
     closest
    -1.43
     thanked
    -1.42
     anyone
    -1.40
     slightly
    -1.37
     somehow
    -1.36
    iter
    -1.35
     Then
    -1.34
     ?>
    -1.33
     your
    -1.32
    POSITIVE LOGITS
    "}](#
    1.93
    aceut
    1.90
    cript
    1.86
     era
    1.76
    ificial
    1.74
    ignment
    1.73
    INST
    1.72
    CRIPT
    1.70
    ycin
    1.62
    igue
    1.57
    Activations Density 0.019%

    No Known Activations