© 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. 11020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    226
    +0.10
    0.6%
    95
    +0.10
    0.5%
    376
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.10
    0.00
    1
    -0.10
    0.00
    2
    -0.10
    0.00
    Negative Logits
    rance
    -2.00
    als
    -1.83
    aire
    -1.69
    iana
    -1.67
    nen
    -1.60
     Springer
    -1.59
    theless
    -1.43
    ians
    -1.39
    ards
    -1.38
    arden
    -1.38
    POSITIVE LOGITS
     Nexus
    1.61
    laid
    1.49
    plays
    1.42
     inbox
    1.40
     HTTP
    1.34
    written
    1.34
    ject
    1.33
     SSL
    1.32
     weeks
    1.31
    ressions
    1.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.