© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28889
    Prev
    Next
    INDEX
    Explanations

    structured data and summaries in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    461
    +0.14
    0.8%
    287
    +0.13
    0.8%
    198
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.14
    0.05
    21
    +0.13
    0.04
    461
    +0.13
    0.05
    Negative Logits
    dala
    -1.50
    inib
    -1.48
     soda
    -1.42
     interested
    -1.41
    nai
    -1.40
    )](
    -1.36
    sit
    -1.32
    egg
    -1.31
    erty
    -1.30
    .’”
    -1.30
    POSITIVE LOGITS
    bound
    1.63
     reflections
    1.53
     COPYRIGHT
    1.43
     Apply
    1.42
     Dictionary
    1.40
     Register
    1.37
     Invalid
    1.34
     hereby
    1.33
     Redistributions
    1.32
     exceptions
    1.29
    Activations Density 0.558%

    No Known Activations