© 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. 14639
    Prev
    Next
    INDEX
    Explanations

    elements related to file and service management commands in a computing 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/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
    17
    +0.13
    0.7%
    350
    +0.11
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.27
    156
    +0.11
    0.20
    71
    +0.10
    0.19
    Negative Logits
    ase
    -1.85
    ously
    -1.80
    etically
    -1.70
    ically
    -1.67
    ylase
    -1.51
    ally
    -1.42
     afford
    -1.42
    pector
    -1.42
    ilate
    -1.41
    ually
    -1.40
    POSITIVE LOGITS
    ĭ
    3.82
    ¡
    3.72
    ĥ
    3.70
    Į
    3.67
    Ĭ
    3.58
    ł
    3.53
    ®
    3.52
    İ
    3.47
      ↵
    3.46
    ↵
    3.45
    Activations Density 0.706%

    No Known Activations