© 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. Residuals
    9. 2-RES-SM
    11. 30744
    Prev
    Next
    INDEX
    Explanations

    import statements in code

    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
    93
    +0.11
    0.6%
    112
    +0.10
    0.6%
    12
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.11
    0.02
    131
    +0.10
    0.02
    385
    +0.10
    0.01
    Negative Logits
    pie
    -1.56
    ittle
    -1.47
    lasting
    -1.45
    absor
    -1.39
    aska
    -1.39
     resided
    -1.39
     fought
    -1.38
    mare
    -1.38
     induced
    -1.38
    ozo
    -1.37
    POSITIVE LOGITS
    ↵
    3.10
    ↵↵↵
    3.10
    ↵
    3.10
              ↵
    3.10
    3.10
    ↵
    3.10
    3.10
     ↵
    3.10
    ↵
    3.10
    ↵
    3.10
    Activations Density 0.074%

    No Known Activations