© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 10812
    Prev
    Next
    INDEX
    Explanations

    references to various types of manufacturers and their relationships to products and consumers

    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
    156
    +0.16
    0.9%
    119
    +0.13
    0.7%
    244
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.16
    0.04
    73
    +0.13
    0.03
    184
    +0.12
    0.03
    Negative Logits
    ĥ½
    -1.61
     viral
    -1.47
    oning
    -1.42
    oned
    -1.40
     former
    -1.38
     Sacred
    -1.37
    ŀ
    -1.35
    ppler
    -1.34
    urnal
    -1.34
    erring
    -1.33
    POSITIVE LOGITS
    ship
    2.46
    liness
    1.97
    ial
    1.86
    hood
    1.82
    ships
    1.81
    dom
    1.73
    esses
    1.69
    ielle
    1.68
     liable
    1.67
    ials
    1.66
    Activations Density 0.419%

    No Known Activations