© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or ways to achieve outcomes

    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
    78
    +0.15
    0.9%
    476
    +0.14
    0.8%
    63
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.15
    0.02
    256
    +0.14
    0.02
    365
    +0.12
    0.02
    Negative Logits
     Photograph
    -2.08
    grily
    -1.56
     accession
    -1.55
     respectively
    -1.52
    .’”
    -1.49
    \]](
    -1.45
     bankrupt
    -1.36
    ,’
    -1.34
    UTERS
    -1.33
    iless
    -1.33
    POSITIVE LOGITS
    Ļ
    2.74
    ³
    2.56
    ¹
    2.49
    2.49
    2.49
    ↵        ↵
    2.49
    2.49
    <|outofrange|>
    2.49
    2.49
     ↵
    2.49
    Activations Density 0.112%

    No Known Activations