© 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. 30379
    Prev
    Next
    INDEX
    Explanations

    instances of specific high-frequency characters or symbols

    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
    125
    +0.14
    0.8%
    203
    +0.14
    0.8%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.14
    0.01
    125
    +0.14
    0.01
    59
    +0.12
    0.01
    Negative Logits
    ferenced
    -1.72
     quo
    -1.63
    MOESM
    -1.53
     ?"
    -1.46
    ±
    -1.46
    ·
    -1.41
    openh
    -1.41
    ferencing
    -1.40
    »
    -1.35
     Fig
    -1.34
    POSITIVE LOGITS
    etts
    1.65
    à±ģ
    1.57
    iliar
    1.55
    iating
    1.50
    ellation
    1.44
    enance
    1.40
    arts
    1.38
    meg
    1.38
     questioning
    1.36
    cases
    1.34
    Activations Density 0.064%

    No Known Activations