© 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. 29589
    Prev
    Next
    INDEX
    Explanations

    non-standard characters or encoding errors in the text

    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
    2
    +0.15
    0.8%
    484
    +0.13
    0.7%
    286
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.02
    322
    +0.13
    0.02
    455
    +0.12
    0.02
    Negative Logits
     chosen
    -1.84
     manners
    -1.66
     nowhere
    -1.54
     nearest
    -1.47
    azine
    -1.47
     designated
    -1.43
     crashed
    -1.43
     announced
    -1.41
     suddenly
    -1.38
     apologized
    -1.38
    POSITIVE LOGITS
    suppl
    1.78
    using
    1.71
    eva
    1.68
    fonts
    1.64
    @{
    1.63
    vist
    1.60
    /-/
    1.58
    amsbsy
    1.54
    court
    1.52
    ¡
    1.51
    Activations Density 1.746%

    No Known Activations