© 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. 29265
    Prev
    Next
    INDEX
    Explanations

    mentions of musical performances and artists

    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
    +0.24
    1.4%
    87
    +0.15
    0.9%
    148
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.24
    0.02
    111
    +0.15
    0.02
    271
    +0.11
    0.01
    Negative Logits
     recent
    -1.61
     previous
    -1.51
     EEOC
    -1.46
    ETHOD
    -1.45
     subsequent
    -1.41
    unnumbered
    -1.39
    ellant
    -1.38
     hr
    -1.38
     federal
    -1.37
     sudden
    -1.35
    POSITIVE LOGITS
    ties
    2.34
    ty
    1.98
    makers
    1.93
    ulators
    1.83
    izers
    1.79
    isms
    1.77
    ists
    1.72
    ized
    1.69
    s
    1.67
    ised
    1.65
    Activations Density 0.169%

    No Known Activations