© 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. 28232
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those related to measurements or quantities

    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
    198
    +0.14
    0.8%
    153
    +0.14
    0.8%
    406
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.09
    198
    +0.14
    0.07
    153
    +0.13
    0.05
    Negative Logits
    erie
    -1.55
    quart
    -1.54
    aine
    -1.45
    anne
    -1.45
    etics
    -1.39
    igated
    -1.36
     Anonymous
    -1.33
    omy
    -1.31
    olan
    -1.30
    aceae
    -1.29
    POSITIVE LOGITS
    inner
    1.92
     intervals
    1.58
     increments
    1.51
    inners
    1.50
    000
    1.50
     altitude
    1.46
    gers
    1.40
     distance
    1.39
     window
    1.39
    rivers
    1.36
    Activations Density 1.451%

    No Known Activations