© 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. 4-RES-SM
    11. 10359
    Prev
    Next
    INDEX
    Explanations

    references to different intensities or qualities of light

    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
    466
    +0.17
    1.0%
    119
    +0.12
    0.7%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.17
    0.03
    119
    +0.12
    0.03
    443
    +0.11
    0.03
    Negative Logits
    ould
    -1.83
    ĻĤ
    -1.78
    hips
    -1.68
    reement
    -1.65
    uld
    -1.60
    imental
    -1.59
    ators
    -1.57
    Ĺ
    -1.55
    OMEM
    -1.52
    ate
    -1.52
    POSITIVE LOGITS
    ening
    2.77
    ened
    2.41
    hearted
    2.36
     bulb
    2.36
     bulbs
    2.34
    nings
    2.33
    curve
    2.31
    est
    2.29
    bul
    2.23
    cone
    2.19
    Activations Density 0.219%

    No Known Activations