© 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. 4-RES-SM
    11. 13337
    Prev
    Next
    INDEX
    Explanations

    terms related to management and organizational strategies

    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
    156
    +0.31
    1.8%
    198
    +0.11
    0.6%
    177
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.31
    0.10
    18
    +0.11
    0.08
    11
    +0.10
    0.05
    Negative Logits
    derer
    -1.99
    ches
    -1.77
    ั
    -1.74
    ะ
    -1.70
    ีà¹Ī
    -1.69
    athi
    -1.67
    ане
    -1.65
    Ûķ
    -1.63
    ี
    -1.61
    ὶ
    -1.60
    POSITIVE LOGITS
    ity
    2.43
     design
    2.05
     delivery
    2.05
     deployment
    1.98
     positioning
    1.98
    ¯
    1.98
    zza
    1.96
     communication
    1.94
     scheduling
    1.94
     use
    1.93
    Activations Density 0.947%

    No Known Activations