© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 31758
    Prev
    Next
    INDEX
    Explanations

    references to electric power mechanisms and their configurations

    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
    263
    +0.17
    1.0%
    379
    +0.12
    0.7%
    469
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.17
    0.08
    47
    +0.12
    0.08
    61
    +0.12
    0.06
    Negative Logits
     msgid
    -1.77
    substring
    -1.75
    inction
    -1.72
    ificance
    -1.69
     bitterness
    -1.65
    ITERATION
    -1.62
    hesis
    -1.59
    result
    -1.58
     onset
    -1.57
     spell
    -1.54
    POSITIVE LOGITS
     appliances
    1.98
     computers
    1.98
     hardware
    1.88
     automobiles
    1.82
     portable
    1.79
     machines
    1.77
     apparatuses
    1.76
     devices
    1.73
     Sony
    1.68
     Electronics
    1.67
    Activations Density 1.057%

    No Known Activations