© 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. 30068
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of charging and discharging, particularly in the context of batteries and electrical energy

    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
    113
    +0.13
    0.7%
    343
    +0.12
    0.7%
    129
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.13
    0.03
    177
    +0.12
    0.02
    113
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -2.82
    ĭ
    -2.34
    ĥ½
    -2.29
    ħ
    -2.23
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -2.21
      ↵
    -2.19
    ↵↵
    -2.19
    -2.19
    <|outofrange|>
    -2.19
    -2.19
    POSITIVE LOGITS
    kowski
    2.28
    ier
    2.13
    backs
    2.05
    forward
    2.03
    ability
    1.98
    back
    1.94
    able
    1.87
    rette
    1.75
    eless
    1.69
    ably
    1.68
    Activations Density 0.139%

    No Known Activations