© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28503
    Prev
    Next
    INDEX
    Explanations

    technical specifications and programming-related content

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    186
    +0.26
    1.6%
    419
    +0.24
    1.5%
    161
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.26
    0.12
    186
    +0.24
    0.07
    161
    +0.17
    0.05
    Negative Logits
     format
    -1.88
     archives
    -1.64
     Caption
    -1.62
     shelves
    -1.59
     freezer
    -1.57
    aliana
    -1.54
     FIGS
    -1.52
     Youtube
    -1.51
     tutorial
    -1.50
    cdn
    -1.48
    POSITIVE LOGITS
     respectively
    1.83
    ities
    1.61
    quo
    1.60
     illness
    1.42
    ials
    1.42
    offs
    1.40
    istic
    1.39
    idity
    1.38
    '];
    1.37
    igion
    1.37
    Activations Density 5.959%

    No Known Activations