© 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. 28302
    Prev
    Next
    INDEX
    Explanations

    instances of legal violations

    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
    156
    +0.17
    0.9%
    317
    +0.13
    0.7%
    412
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.17
    0.03
    387
    +0.13
    0.03
    480
    +0.11
    0.03
    Negative Logits
    iller
    -1.69
     expressed
    -1.65
    erred
    -1.51
    erne
    -1.44
     hormone
    -1.41
    chos
    -1.37
    fired
    -1.36
    iler
    -1.36
    ilers
    -1.34
    er
    -1.33
    POSITIVE LOGITS
    ¿
    2.86
    İ
    2.56
    ł
    2.52
    Ļ
    2.52
    ¾
    2.50
    Į
    2.46
    Ĥ¬
    2.44
    į
    2.40
    §
    2.39
    ²
    2.38
    Activations Density 0.077%

    No Known Activations