© 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. 1-RES-SM
    11. 25513
    Prev
    Next
    INDEX
    Explanations

    terms related to acoustic properties and sound

    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
    1.3%
    148
    +0.15
    0.9%
    443
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.22
    0.04
    156
    +0.15
    0.03
    271
    +0.14
    0.01
    Negative Logits
     aligned
    -1.61
     everyone
    -1.57
    asty
    -1.57
     ital
    -1.45
     appointed
    -1.43
    stant
    -1.43
     deciding
    -1.41
     everybody
    -1.39
     capital
    -1.38
     exact
    -1.38
    POSITIVE LOGITS
     guitar
    1.64
    iences
    1.60
    cone
    1.57
    mouth
    1.57
    oustic
    1.55
    acia
    1.54
     guitars
    1.53
    ines
    1.53
    scape
    1.53
    caster
    1.51
    Activations Density 0.133%

    No Known Activations