© 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. 1-RES-SM
    11. 27296
    Prev
    Next
    INDEX
    Explanations

    mentions of electronic devices and technology

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.30
    1.8%
    365
    +0.14
    0.8%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.30
    0.02
    144
    +0.14
    0.02
    91
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.99
    -2.91
    <|outofrange|>
    -2.91
     ↵
    -2.91
    <|outofrange|>
    -2.91
    -2.91
    -2.91
     ↵
    -2.91
    -2.91
      ↵
    -2.91
    POSITIVE LOGITS
    etting
    1.88
    ystems
    1.82
    olve
    1.80
     comprising
    1.77
    urgical
    1.76
     capable
    1.76
    creen
    1.68
    oid
    1.66
    olutions
    1.63
    urable
    1.63
    Activations Density 0.046%

    No Known Activations