© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28095
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those with the name "Herman" or "Hassan."

    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
    156
    +0.15
    0.8%
    466
    +0.13
    0.7%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.15
    0.01
    332
    +0.13
    0.01
    31
    +0.12
    0.01
    Negative Logits
     gay
    -1.65
     transgender
    -1.65
     Hispanic
    -1.54
     birth
    -1.49
    oring
    -1.48
     western
    -1.47
     Caribbean
    -1.43
     roll
    -1.43
     release
    -1.41
    ards
    -1.36
    POSITIVE LOGITS
    ilee
    1.83
    cules
    1.75
    stown
    1.66
    owitz
    1.65
    stadt
    1.65
    jee
    1.64
    ovsk
    1.63
    iewicz
    1.62
    ии
    1.61
    opan
    1.58
    Activations Density 0.035%

    No Known Activations