© 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 EvalsExportsinterp-engineNEWAPI 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. 24683
    Prev
    Next
    INDEX
    Explanations

    terms related to combustion and fuel types

    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
    37
    +0.17
    1.0%
    456
    +0.12
    0.7%
    113
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.17
    0.01
    456
    +0.12
    0.01
    131
    +0.11
    0.01
    Negative Logits
    ĻĤ
    -2.00
    ···
    -1.71
     '\
    -1.52
    ureus
    -1.48
    ť
    -1.47
    Ŀ
    -1.42
    unnumbered
    -1.41
    ŀ
    -1.41
     classmates
    -1.40
    wered
    -1.40
    POSITIVE LOGITS
     fires
    1.76
    iston
    1.68
     combustion
    1.65
    sten
    1.56
     machinery
    1.54
     laws
    1.53
     ourselves
    1.52
    engine
    1.52
     phenomena
    1.49
    shall
    1.49
    Activations Density 0.064%

    No Known Activations