© 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. 14003
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to neural signaling and mechanisms

    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
    253
    +0.13
    0.7%
    498
    +0.13
    0.7%
    25
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.06
    111
    +0.13
    0.07
    274
    +0.13
    0.07
    Negative Logits
     warranty
    -2.04
     adul
    -1.98
     UAE
    -1.80
     pricing
    -1.76
     wine
    -1.75
    ibles
    -1.72
    bestos
    -1.70
     Shipping
    -1.68
     customs
    -1.67
     premium
    -1.64
    POSITIVE LOGITS
     neurons
    4.00
     neuronal
    3.60
     neuron
    3.57
     axons
    3.43
     excitatory
    3.34
     axonal
    3.31
     cortical
    3.25
     neural
    3.24
     synapses
    3.19
     synaptic
    3.13
    Activations Density 0.655%

    No Known Activations