© 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. 11111
    Prev
    Next
    INDEX
    Explanations

    scientific or technical jargon and names in a document

    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
    64
    +0.29
    1.7%
    307
    +0.19
    1.1%
    216
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.29
    0.11
    162
    +0.19
    0.03
    216
    +0.15
    0.05
    Negative Logits
    ogue
    -1.91
    ioned
    -1.74
    iei
    -1.73
    ings
    -1.69
    itary
    -1.68
    Than
    -1.68
    asone
    -1.68
    sey
    -1.62
    aign
    -1.53
    ington
    -1.52
    POSITIVE LOGITS
    ÑĨи
    3.09
    ем
    3.08
    Ñıм
    3.04
    ÑĨии
    3.00
    ÑĪе
    2.96
    ÑĨиÑı
    2.94
    ÑĤоÑĢ
    2.84
    ев
    2.80
    Ñİ
    2.78
    еÑģк
    2.78
    Activations Density 0.116%

    No Known Activations