© 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. 24835
    Prev
    Next
    INDEX
    Explanations

    Python import statements

    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
    174
    +0.13
    0.7%
    372
    +0.13
    0.7%
    309
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.13
    0.04
    174
    +0.13
    0.04
    309
    +0.13
    0.03
    Negative Logits
     devoted
    -1.65
    IPE
    -1.42
    ICH
    -1.42
     suited
    -1.42
     cancer
    -1.36
    kinase
    -1.36
    ozo
    -1.33
     Alzheimer
    -1.33
    ipes
    -1.33
     dedicated
    -1.32
    POSITIVE LOGITS
    antly
    2.11
    erre
    1.65
    erson
    1.64
    anz
    1.62
    ell
    1.49
    uring
    1.49
    umably
    1.48
     shelves
    1.46
    ray
    1.44
    eric
    1.41
    Activations Density 0.042%

    No Known Activations