© 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. 30133
    Prev
    Next
    INDEX
    Explanations

    mentions of specific software or service categories

    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
    246
    +0.12
    0.7%
    108
    +0.12
    0.7%
    319
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.02
    89
    +0.12
    0.02
    108
    +0.10
    0.02
    Negative Logits
     sudden
    -1.97
     cry
    -1.74
     welcome
    -1.66
     pregnant
    -1.64
     quick
    -1.62
     vomiting
    -1.60
     thee
    -1.55
     disbelief
    -1.54
     lean
    -1.54
     pooled
    -1.53
    POSITIVE LOGITS
    creen
    1.81
    CRIPT
    1.80
     (“
    1.77
    chap
    1.75
    ENTIAL
    1.75
    mith
    1.73
    burg
    1.71
    cript
    1.70
    film
    1.69
    boro
    1.69
    Activations Density 0.007%

    No Known Activations