© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28192
    Prev
    Next
    INDEX
    Explanations

    highly specific numerical data and parameters

    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
    203
    +0.16
    0.9%
    369
    +0.15
    0.9%
    82
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.16
    0.04
    203
    +0.15
    0.05
    477
    +0.15
    0.05
    Negative Logits
     quo
    -2.07
     warfare
    -1.85
     ).
    -1.61
    merce
    -1.56
    ľĵ
    -1.49
    pires
    -1.46
     linking
    -1.43
    OutputStream
    -1.43
    lique
    -1.40
     meantime
    -1.35
    POSITIVE LOGITS
    7554
    1.79
     asp
    1.69
     minutes
    1.65
    itars
    1.64
    ths
    1.61
    \%
    1.54
    ycin
    1.51
    uis
    1.48
     Minutes
    1.46
    gi
    1.44
    Activations Density 0.132%

    No Known Activations