© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 9416
    Prev
    Next
    INDEX
    Explanations

    connections and relationships among items or concepts in a list format

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    466
    +0.27
    1.5%
    307
    +0.15
    0.9%
    377
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.27
    0.11
    377
    +0.15
    0.09
    154
    +0.11
    0.08
    Negative Logits
    Ĥ¬
    -2.69
    »
    -2.42
    ·
    -2.42
    ĨĴ
    -2.31
    ¹
    -2.26
    ĻĤ
    -2.11
    ĭ
    -2.02
    ĸ´
    -1.94
    ij
    -1.88
    FFIRMED
    -1.88
    POSITIVE LOGITS
     omissions
    2.52
     structures
    2.48
     orientations
    2.46
     frameworks
    2.41
     associations
    2.39
     distributions
    2.35
     assemblies
    2.34
     constructs
    2.33
     sizes
    2.33
     labels
    2.31
    Activations Density 0.777%

    No Known Activations