© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    references to yeast and fungi

    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
    +0.23
    1.3%
    466
    +0.12
    0.7%
    397
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.03
    156
    +0.12
    0.02
    271
    +0.12
    0.01
    Negative Logits
    adeon
    -1.58
     \%
    -1.51
     '</
    -1.49
    textrm
    -1.47
     para
    -1.45
    gg
    -1.44
    estinal
    -1.40
    linewidth
    -1.38
    qq
    -1.37
    aras
    -1.34
    POSITIVE LOGITS
    Ĵ
    1.84
    beans
    1.62
    scape
    1.61
    buntu
    1.59
    cles
    1.57
    cript
    1.52
    flies
    1.49
     alone
    1.49
    erals
    1.47
     itself
    1.44
    Activations Density 0.129%

    No Known Activations