© 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. 10534
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters in text

    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
    155
    +0.12
    0.7%
    271
    +0.12
    0.7%
    281
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.12
    0.02
    502
    +0.12
    0.02
    312
    +0.11
    0.02
    Negative Logits
    omyces
    -1.94
    ."""
    -1.84
    .[]{
    -1.70
    .\"
    -1.66
    """
    -1.63
    "}](#
    -1.61
     footing
    -1.51
     wip
    -1.50
    merce
    -1.46
    $.[]{
    -1.44
    POSITIVE LOGITS
     ),
    3.03
     )
    2.78
     ).
    2.50
    -)
    2.38
     ):
    2.34
    )_
    2.21
    ),
    2.16
     );
    2.13
     ")
    2.06
    ,)
    2.04
    Activations Density 0.080%

    No Known Activations