© 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. 2-RES-SM
    11. 28528
    Prev
    Next
    INDEX
    Explanations

    questions that can be answered with numeric values or related calculations

    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
    478
    +0.14
    0.8%
    8
    +0.11
    0.6%
    115
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    8
    +0.14
    0.01
    357
    +0.11
    0.01
    367
    +0.10
    0.01
    Negative Logits
    listed
    -1.77
    quarters
    -1.53
     futures
    -1.53
    tests
    -1.52
    caster
    -1.51
     boards
    -1.50
    through
    -1.46
     papers
    -1.46
     notes
    -1.45
    notes
    -1.44
    POSITIVE LOGITS
    »
    2.00
    ĩ
    1.76
    IJ
    1.75
    ¯
    1.74
    ·
    1.73
    ±
    1.62
    ´
    1.62
    Ł
    1.59
    ĥ½
    1.58
    ¹
    1.56
    Activations Density 0.025%

    No Known Activations