Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26918
    Prev
    Next
    INDEX
    Explanations

    references to musical instruments and musicians

    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
    +0.12
    0.7%
    16
    +0.11
    0.6%
    443
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.03
    443
    +0.11
    0.03
    321
    +0.10
    0.03
    Negative Logits
     least
    -1.81
    icable
    -1.77
    amacare
    -1.53
     Planned
    -1.49
     previous
    -1.47
     pers
    -1.41
    AMA
    -1.41
     Mons
    -1.39
    anu
    -1.38
     Pinterest
    -1.38
    POSITIVE LOGITS
    ettes
    1.85
    uitar
    1.83
    uple
    1.80
     solo
    1.78
    ksen
    1.77
     music
    1.76
     bass
    1.74
     guitar
    1.74
    hythm
    1.71
     fans
    1.71
    Activations Density 0.273%

    No Known Activations