© 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. 2-RES-SM
    11. 30128
    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
    501
    +0.14
    0.8%
    319
    +0.13
    0.7%
    366
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.13
    0.00
    2
    -0.11
    0.00
    Negative Logits
    PED
    -1.48
    Syscall
    -1.43
    si
    -1.42
    chte
    -1.40
     silent
    -1.40
    80211
    -1.37
    PING
    -1.35
     Springer
    -1.33
     fus
    -1.33
    igen
    -1.32
    POSITIVE LOGITS
    Ł
    2.48
    ĸ
    1.94
    ¤
    1.77
    ł
    1.74
    ij
    1.73
    ¡
    1.70
    ļ
    1.65
    krit
    1.61
    ī
    1.60
    Ĩ
    1.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.