© 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. 28341
    Prev
    Next
    INDEX
    Explanations

    references to the Internet, particularly in the context of its impact and governance

    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
    451
    +0.12
    0.7%
    490
    +0.11
    0.6%
    432
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.12
    0.03
    432
    +0.11
    0.03
    490
    +0.10
    0.02
    Negative Logits
     tear
    -2.02
     solitary
    -1.69
     queer
    -1.58
     biggest
    -1.57
     temporary
    -1.56
    ce
    -1.56
     smallest
    -1.51
     gon
    -1.50
     full
    -1.49
     little
    -1.49
    POSITIVE LOGITS
    borne
    1.93
    obi
    1.88
    obox
    1.78
    amente
    1.74
    ilee
    1.70
    bank
    1.68
    bourne
    1.66
    iac
    1.65
    ström
    1.64
    ophone
    1.62
    Activations Density 0.323%

    No Known Activations