© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1-RES-SM
    6. 26548
    Prev
    Next
    INDEX
    Explanations

    references to traditional or standard methods and practices

    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
    +0.25
    1.4%
    433
    +0.14
    0.8%
    128
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.25
    0.01
    418
    +0.14
    0.01
    270
    +0.13
    0.01
    Negative Logits
    lot
    -1.73
    obacterium
    -1.66
    '">
    -1.55
     cleaved
    -1.54
     0000000000000000000000000000000000
    -1.51
    oto
    -1.47
     unfolded
    -1.46
    Å¡ÃŃ
    -1.41
     µl
    -1.40
    â̲-
    -1.38
    POSITIVE LOGITS
    izations
    1.82
    izing
    1.78
     wisdom
    1.77
    £
    1.72
     explanations
    1.62
     applications
    1.61
     opinions
    1.60
    isations
    1.60
     marriages
    1.56
    ising
    1.51
    Activations Density 0.041%

    No Known Activations