© 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. 1-RES-SM
    11. 26547
    Prev
    Next
    INDEX
    Explanations

    instances of significant medical conditions and their impacts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    153
    +0.14
    0.8%
    496
    +0.13
    0.7%
    87
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.01
    84
    +0.13
    0.01
    338
    +0.12
    0.01
    Negative Logits
    ÃŃv
    -1.79
     clauses
    -1.63
    oupe
    -1.57
    imental
    -1.56
    osa
    -1.51
    imento
    -1.40
    uez
    -1.40
    iment
    -1.39
    orter
    -1.39
     exception
    -1.36
    POSITIVE LOGITS
    »
    4.15
    č↵
    3.98
    ↵↵
    3.98
    3.98
    3.98
    3.98
    3.98
    3.98
    ↵
    3.98
    ↵
    3.98
    Activations Density 0.002%

    No Known Activations