© 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 EvalsExportsinterp-engineNEWAPI 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. 29855
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "MS," which likely refers to multiple sclerosis or Microsoft-related topics

    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
    369
    +0.17
    1.0%
    376
    +0.15
    0.8%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.17
    0.02
    89
    +0.15
    0.01
    0
    +0.12
    0.01
    Negative Logits
     dozen
    -1.70
     my
    -1.68
     yours
    -1.57
     voluntary
    -1.54
     other
    -1.52
     what
    -1.51
     others
    -1.46
     our
    -1.46
    sing
    -1.44
     sudden
    -1.43
    POSITIVE LOGITS
    NBC
    1.79
    FC
    1.77
    FW
    1.67
    holes
    1.64
    film
    1.63
    IER
    1.61
    VC
    1.58
    OUTPUT
    1.54
    hart
    1.53
    opan
    1.52
    Activations Density 0.087%

    No Known Activations