© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 11083
    Prev
    Next
    INDEX
    Explanations

    references to specific studies or reports

    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
    21
    +0.14
    0.8%
    397
    +0.10
    0.6%
    315
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.14
    0.03
    14
    +0.10
    0.03
    425
    +0.09
    0.03
    Negative Logits
    ilate
    -1.57
    aved
    -1.53
    esty
    -1.50
    yards
    -1.38
    =$
    -1.36
    exe
    -1.34
    quo
    -1.31
    <-
    -1.31
    experienced
    -1.31
    ids
    -1.31
    POSITIVE LOGITS
     study
    2.65
     research
    2.25
     investigation
    2.25
     studies
    2.12
     article
    2.08
     proposal
    1.95
     Study
    1.86
     investigations
    1.84
     endeavor
    1.82
     methodology
    1.80
    Activations Density 0.063%

    No Known Activations