© 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. 28403
    Prev
    Next
    INDEX
    Explanations

    elements associated with physical attributes and conditions

    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
    153
    +0.17
    1.0%
    293
    +0.13
    0.8%
    141
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.17
    0.07
    293
    +0.13
    0.11
    401
    +0.12
    0.10
    Negative Logits
     Commerce
    -1.90
    blogger
    -1.82
     behalf
    -1.66
     Market
    -1.58
    undry
    -1.56
     Estate
    -1.56
     Charter
    -1.50
     College
    -1.50
     University
    -1.48
     personally
    -1.48
    POSITIVE LOGITS
    liness
    2.00
    heses
    1.79
    =”
    1.72
    inations
    1.69
    ishly
    1.53
    esses
    1.50
    dings
    1.50
    ility
    1.49
    umes
    1.49
    iles
    1.49
    Activations Density 3.395%

    No Known Activations