© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11976
    Prev
    Next
    INDEX
    Explanations

    evidence of revealed findings in scientific data related to various experiments or studies

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.16
    0.9%
    23
    +0.13
    0.8%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.16
    0.03
    283
    +0.13
    0.04
    324
    +0.12
    0.03
    Negative Logits
    zent
    -1.61
    lit
    -1.54
    ½
    -1.51
     philosophy
    -1.49
    /)
    -1.48
    arium
    -1.46
    uary
    -1.46
    ilee
    -1.46
    ce
    -1.45
     doctrine
    -1.45
    POSITIVE LOGITS
     significant
    2.37
     widespread
    2.19
     substantial
    2.19
     negligible
    2.13
     gradual
    2.01
     considerable
    2.00
     strong
    1.99
     decrease
    1.99
     rapid
    1.98
     frequent
    1.97
    Activations Density 0.267%

    No Known Activations