© 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. 29926
    Prev
    Next
    INDEX
    Explanations

    parentheses and single quotes

    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
    185
    +0.14
    0.7%
    404
    +0.10
    0.6%
    409
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.14
    0.24
    486
    +0.10
    0.17
    154
    +0.09
    0.15
    Negative Logits
    ļ
    -1.65
    ĸ
    -1.62
    ®
    -1.54
     chances
    -1.49
    hill
    -1.41
    tik
    -1.39
    *;
    -1.37
    Ļ
    -1.37
    meg
    -1.35
    case
    -1.33
    POSITIVE LOGITS
    inks
    1.71
    mas
    1.50
    oons
    1.44
     embol
    1.44
     lighter
    1.42
    hers
    1.41
    ishes
    1.40
     sinks
    1.40
    ielder
    1.39
     boarded
    1.38
    Activations Density 0.455%

    No Known Activations