© 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. 2-RES-SM
    11. 32106
    Prev
    Next
    INDEX
    Explanations

    references to numerical values, particularly in a programming or analytical context

    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
    369
    +0.17
    0.9%
    235
    +0.14
    0.8%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.17
    0.01
    374
    +0.14
    0.01
    495
    +0.12
    0.01
    Negative Logits
    orems
    -1.61
    iners
    -1.61
     gradients
    -1.54
    inen
    -1.48
    ...](
    -1.47
    ](
    -1.44
    aris
    -1.43
     '$
    -1.38
    ymers
    -1.38
    ?",
    -1.37
    POSITIVE LOGITS
    documentclass
    1.58
    dot
    1.44
    %.
    1.41
    emis
    1.41
    Discussion
    1.40
    boro
    1.39
     lit
    1.34
    Summary
    1.31
    TB
    1.30
     Representative
    1.27
    Activations Density 0.025%

    No Known Activations