© 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 EvalsExportsinterp-engineNEWAPI 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. 29331
    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
    325
    +0.13
    0.7%
    113
    +0.12
    0.7%
    441
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.12
    0.00
    2
    -0.12
    0.00
    Negative Logits
    eps
    -1.61
    immer
    -1.52
    hip
    -1.49
    eter
    -1.48
     blocker
    -1.46
     blockers
    -1.44
    elf
    -1.44
     gay
    -1.42
    hips
    -1.40
     spirit
    -1.39
    POSITIVE LOGITS
    ¿
    3.52
    ¯
    3.46
    İ
    3.29
    µ
    3.24
    »
    3.22
    Īĺ
    3.19
    3.19
    3.19
    ↵
    3.19
    ↵
    3.19
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.