© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 30563
    Prev
    Next
    INDEX
    Explanations

    terms related to optimization processes

    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
    156
    +0.12
    0.7%
    66
    +0.12
    0.6%
    203
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.12
    0.03
    85
    +0.12
    0.01
    77
    +0.11
    0.01
    Negative Logits
    à±ģ
    -1.68
    áĢº
    -1.53
     responsibility
    -1.53
     lining
    -1.50
    áĢ¯
    -1.49
     conviction
    -1.47
     preponderance
    -1.42
    GREEK
    -1.42
    stanbul
    -1.41
    contents
    -1.39
    POSITIVE LOGITS
    imization
    2.32
    imize
    2.28
    imus
    1.98
    imum
    1.83
    imates
    1.74
    imal
    1.67
    imate
    1.59
    genstein
    1.52
    iator
    1.50
    ivat
    1.46
    Activations Density 0.126%

    No Known Activations