© 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. 10753
    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
    213
    +0.12
    0.7%
    116
    +0.12
    0.6%
    473
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.12
    0.00
    1
    -0.12
    0.00
    2
    -0.10
    0.00
    Negative Logits
    ħ
    -2.69
    ķ
    -2.64
    ī
    -2.49
    ¹
    -2.28
    Ĩ
    -2.18
    ı
    -2.18
    °
    -2.17
    į
    -2.15
    ĸ´
    -2.15
    Ģ
    -2.10
    POSITIVE LOGITS
    ska
    2.00
    ="../../../../../../
    1.69
    lag
    1.60
    sdl
    1.54
    eLife
    1.51
    frastructure
    1.48
    ijk
    1.44
    iasis
    1.42
    endpoint
    1.41
    ="../../../../../
    1.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.