© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28168
    Prev
    Next
    INDEX
    Explanations

    instances of the word "one"

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    436
    +0.13
    0.7%
    144
    +0.13
    0.7%
    87
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.13
    0.05
    239
    +0.13
    0.06
    87
    +0.12
    0.04
    Negative Logits
    ional
    -1.77
    ions
    -1.72
    orate
    -1.65
    ores
    -1.63
    ors
    -1.62
    rypt
    -1.59
    oration
    -1.51
    riages
    -1.51
    ards
    -1.51
    rans
    -1.46
    POSITIVE LOGITS
     hundred
    2.11
     thousand
    1.84
     crore
    1.79
     trillion
    1.79
    hundred
    1.78
     million
    1.75
     dozen
    1.69
     Hundred
    1.68
     billion
    1.66
    veh
    1.61
    Activations Density 0.155%

    No Known Activations