© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27111
    Prev
    Next
    INDEX
    Explanations

    expressions of significant emotional events or experiences

    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
    292
    +0.14
    0.8%
    108
    +0.12
    0.6%
    460
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.14
    0.51
    56
    +0.12
    0.16
    203
    +0.12
    0.35
    Negative Logits
    unnumbered
    -1.77
    documentclass
    -1.55
     interest
    -1.54
    ipro
    -1.52
     unanimously
    -1.38
    imetry
    -1.38
     hereafter
    -1.37
     convenience
    -1.37
    {$
    -1.37
    ive
    -1.36
    POSITIVE LOGITS
    vier
    1.76
    hoe
    1.55
    avian
    1.50
    izumab
    1.48
    **](#
    1.48
    aber
    1.47
    ingly
    1.45
     DC
    1.44
    anda
    1.44
    athan
    1.43
    Activations Density 3.650%

    No Known Activations