© 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. 29146
    Prev
    Next
    INDEX
    Explanations

    sentences that conclude with a period

    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
    23
    +0.54
    4.3%
    258
    +0.27
    2.2%
    156
    +0.24
    2.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.54
    0.55
    56
    +0.27
    0.18
    203
    +0.24
    0.38
    Negative Logits
    ÅĽci
    -2.15
    iewicz
    -1.95
    ermann
    -1.80
    ek
    -1.79
    aho
    -1.75
    esan
    -1.74
    endas
    -1.74
    ÃŃf
    -1.73
    ól
    -1.71
    VERTISEMENT
    -1.70
    POSITIVE LOGITS
    rapeutic
    1.83
    rapy
    1.72
     finally
    1.69
     simplest
    1.58
    open
    1.57
     NHS
    1.55
    from
    1.51
     sudden
    1.50
    rap
    1.49
    rapeutics
    1.44
    Activations Density 7.488%

    No Known Activations