© 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. 25537
    Prev
    Next
    INDEX
    Explanations

    references to advisory roles related to travel or service guides

    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
    432
    +0.11
    0.7%
    109
    +0.11
    0.7%
    187
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.11
    0.01
    109
    +0.11
    0.01
    187
    +0.10
    0.01
    Negative Logits
     substantial
    -1.55
     \}
    -1.55
    \}\
    -1.55
    omers
    -1.55
     antisense
    -1.54
     ?"
    -1.54
    \}
    -1.48
     parted
    -1.47
    ]>
    -1.46
     taste
    -1.45
    POSITIVE LOGITS
    naire
    2.27
    caster
    2.10
    cule
    2.05
    garten
    1.94
    pieces
    1.94
    fecture
    1.81
    haus
    1.79
    maid
    1.78
    ictionary
    1.74
    plots
    1.73
    Activations Density 0.017%

    No Known Activations