© 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 EvalsExportsAPI 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. 28665
    Prev
    Next
    INDEX
    Explanations

    instances of the word "crumb."

    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
    0.8%
    286
    +0.14
    0.8%
    444
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    286
    +0.15
    0.02
    328
    +0.14
    0.02
    444
    +0.13
    0.02
    Negative Logits
    olor
    -1.54
    las
    -1.54
    hip
    -1.53
    OLOR
    -1.53
    oder
    -1.45
     him
    -1.45
     others
    -1.42
     eve
    -1.41
     happening
    -1.40
     jan
    -1.39
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.78
    bugs
    1.72
    enstein
    1.71
    ĻĤ
    1.70
    nail
    1.67
    omyces
    1.52
    church
    1.50
    iop
    1.48
    recht
    1.46
    apest
    1.46
    Activations Density 0.012%

    No Known Activations