© 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. 28422
    Prev
    Next
    INDEX
    Explanations

    references to the name "Fred."

    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
    59
    +0.15
    0.9%
    369
    +0.15
    0.8%
    269
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.02
    1
    +0.15
    0.02
    211
    +0.14
    0.01
    Negative Logits
     distant
    -1.89
    '?"
    -1.73
    "?"
    -1.65
     late
    -1.59
     ease
    -1.59
     hers
    -1.55
     her
    -1.49
     previous
    -1.47
     grade
    -1.46
    jection
    -1.45
    POSITIVE LOGITS
    die
    2.17
    aho
    1.90
    àµį
    1.87
    à«ĩ
    1.86
    asio
    1.84
    eric
    1.78
    holm
    1.74
    shift
    1.73
    tree
    1.69
    ા
    1.67
    Activations Density 0.012%

    No Known Activations