© 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. 28361
    Prev
    Next
    INDEX
    Explanations

    technical, scientific, or engineering processes and their associated terms

    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
    +0.36
    2.1%
    148
    +0.13
    0.7%
    23
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.36
    0.03
    115
    +0.13
    0.05
    462
    +0.11
    0.03
    Negative Logits
    ĥ½
    -3.49
    Į
    -3.38
    ĥ
    -3.22
    č↵
    -3.15
    ↵
    -3.15
    ↵↵
    -3.15
    -3.15
     ↵
    -3.15
    ↵
    -3.15
                  ↵
    -3.15
    POSITIVE LOGITS
     onto
    1.87
     into
    1.82
     surgically
    1.70
     slowly
    1.63
    into
    1.62
    itrogen
    1.61
    oxin
    1.60
    gently
    1.60
     with
    1.57
     paraffin
    1.55
    Activations Density 0.603%

    No Known Activations