© 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. 4-RES-SM
    11. 10626
    Prev
    Next
    INDEX
    Explanations

    highly descriptive language related to product features, particularly in automotive and tech reviews

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.26
    1.5%
    306
    +0.21
    1.2%
    468
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.26
    0.09
    436
    +0.21
    0.05
    377
    +0.12
    0.09
    Negative Logits
    emale
    -1.69
    erculosis
    -1.64
    icans
    -1.53
     petitions
    -1.53
    inib
    -1.52
    ciparum
    -1.52
    izumab
    -1.51
    uximab
    -1.48
    hir
    -1.47
    icions
    -1.46
    POSITIVE LOGITS
    ®
    3.68
    ľĵ
    3.46
    ¿
    3.45
    ↵↵
    3.31
    č↵
    3.31
    č↵
    3.31
    ↵
    3.31
    3.31
    ↵
    3.31
    ↵
    3.31
    Activations Density 1.836%

    No Known Activations