© 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. 29541
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or biological conditions

    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
    71
    +0.16
    0.9%
    362
    +0.14
    0.8%
    444
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    71
    +0.14
    0.01
    320
    +0.12
    0.01
    Negative Logits
    usement
    -1.62
    ĥ
    -1.53
    auc
    -1.45
    fts
    -1.44
     abandon
    -1.42
     ly
    -1.41
    ÑĢоÑģ
    -1.37
    ediatric
    -1.34
    chanical
    -1.34
     promise
    -1.34
    POSITIVE LOGITS
    "}](#
    1.71
    oupe
    1.62
    onymous
    1.61
    bian
    1.55
    ually
    1.48
    agne
    1.46
    erals
    1.41
    holders
    1.38
    burg
    1.36
     clearance
    1.35
    Activations Density 0.004%

    No Known Activations