© 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. 1-RES-SM
    11. 27222
    Prev
    Next
    INDEX
    Explanations

    terms related to folk music and its influences

    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
    156
    +0.22
    1.2%
    87
    +0.17
    0.9%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.22
    0.18
    156
    +0.17
    0.11
    271
    +0.14
    0.06
    Negative Logits
    clusive
    -1.52
    cludes
    -1.52
    CEPT
    -1.44
     processed
    -1.42
     effective
    -1.40
    >&
    -1.38
    PT
    -1.36
    ationally
    -1.35
     Hispanic
    -1.35
     whole
    -1.34
    POSITIVE LOGITS
    bug
    2.04
    bugs
    1.92
    hurst
    1.79
    lor
    1.78
    grass
    1.74
    bird
    1.71
    bane
    1.70
    maid
    1.69
    roots
    1.68
    hammer
    1.68
    Activations Density 0.754%

    No Known Activations