© 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. 4-RES-SM
    11. 11886
    Prev
    Next
    INDEX
    Explanations

    academic or structured content, particularly abstracts and classifications

    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
    156
    +0.56
    3.9%
    111
    +0.22
    1.5%
    271
    +0.20
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.56
    0.04
    199
    +0.22
    0.04
    87
    +0.20
    0.03
    Negative Logits
    č↵
    -3.78
    ↵
    -3.78
    ↵
    -3.78
    <|outofrange|>
    -3.78
    ↵↵
    -3.78
    ↵  ³³³
    -3.78
    <|outofrange|>
    -3.78
    ↵↵
    -3.78
    ↵↵
    -3.78
          ↵
    -3.78
    POSITIVE LOGITS
    mology
    1.35
    iotics
    1.32
    olia
    1.29
    rosis
    1.29
    ане
    1.28
    cribing
    1.25
    ention
    1.22
    olecules
    1.22
    rients
    1.19
    roid
    1.19
    Activations Density 0.049%

    No Known Activations