© 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. 29059
    Prev
    Next
    INDEX
    Explanations

    the word "since" indicating a reference to time or a chronological context

    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
    +0.14
    0.8%
    115
    +0.12
    0.7%
    424
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.14
    0.02
    424
    +0.12
    0.03
    116
    +0.11
    0.03
    Negative Logits
    AIN
    -1.75
    ately
    -1.64
    imetric
    -1.63
    imide
    -1.58
    itud
    -1.55
    ISM
    -1.50
     monitored
    -1.45
     targets
    -1.44
    atories
    -1.37
    targets
    -1.37
    POSITIVE LOGITS
    rely
    1.73
    rey
    1.50
    chaft
    1.46
     vou
    1.42
    union
    1.37
    agna
    1.37
    tons
    1.37
    ?>
    1.35
    Å¡
    1.32
    veolar
    1.32
    Activations Density 1.147%

    No Known Activations