© 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. 1-RES-SM
    11. 28004
    Prev
    Next
    INDEX
    Explanations

    certain patterns or structures within names and designations, possibly focusing on abbreviations or acronyms

    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
    470
    +0.17
    0.9%
    433
    +0.12
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.17
    0.04
    410
    +0.12
    0.04
    346
    +0.11
    0.02
    Negative Logits
    ffe
    -1.75
     Christmas
    -1.57
     handy
    -1.56
     warning
    -1.55
     Abuse
    -1.50
     dere
    -1.46
     Flynn
    -1.43
    quote
    -1.41
     disgrace
    -1.41
     apologize
    -1.40
    POSITIVE LOGITS
    ¶
    1.72
    ¥
    1.72
    enh
    1.71
    ½
    1.69
    tons
    1.67
    Ń
    1.64
    osph
    1.62
    ãĥ¼ãĤ¸
    1.54
    £
    1.54
    ±
    1.53
    Activations Density 0.255%

    No Known Activations