© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27211
    Prev
    Next
    INDEX
    Explanations

    regulatory or compliance terms related to laws or official documents

    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
    169
    +0.12
    0.7%
    201
    +0.11
    0.6%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.12
    0.02
    443
    +0.11
    0.02
    394
    +0.11
    0.02
    Negative Logits
     ">
    -1.85
     welcome
    -1.63
    htt
    -1.57
    xture
    -1.54
    hler
    -1.52
    hower
    -1.45
    hospital
    -1.36
     hypers
    -1.33
    ère
    -1.32
     vez
    -1.31
    POSITIVE LOGITS
    lights
    1.92
    Bs
    1.89
    OUND
    1.73
    bone
    1.69
    nets
    1.69
    rame
    1.68
    derer
    1.67
    ibo
    1.64
    istas
    1.64
    INGS
    1.62
    Activations Density 0.085%

    No Known Activations