© 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. 1-RES-SM
    11. 27160
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    268
    +0.14
    0.7%
    93
    +0.13
    0.7%
    37
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.13
    0.00
    2
    -0.12
    0.00
    Negative Logits
    itic
    -1.54
    iginally
    -1.54
    phrine
    -1.49
     soda
    -1.49
    ascus
    -1.43
    inux
    -1.41
    sterdam
    -1.41
    ahu
    -1.41
    lement
    -1.40
    onical
    -1.36
    POSITIVE LOGITS
     exception
    1.91
    """
    1.67
    encephal
    1.67
    igm
    1.59
    `.
    1.59
     %>
    1.53
    return
    1.51
    ”.
    1.45
     ↵↵
    1.45
     appear
    1.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.