© 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. 12259
    Prev
    Next
    INDEX
    Explanations

    characterized data structures or elements, particularly arrays or collections indicated by bracket notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    302
    +0.16
    0.9%
    130
    +0.14
    0.8%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.16
    0.04
    41
    +0.14
    0.05
    208
    +0.13
    0.05
    Negative Logits
    tons
    -1.95
    icia
    -1.61
    ters
    -1.56
    ania
    -1.54
    cale
    -1.53
    hold
    -1.53
    wat
    -1.48
    imate
    -1.47
    rons
    -1.45
    points
    -1.43
    POSITIVE LOGITS
     ole
    1.56
    unnumbered
    1.54
    xspace
    1.44
    gmail
    1.42
    úblic
    1.39
    Jackson
    1.30
    ÑĤоÑĢ
    1.27
    enn
    1.26
    aturing
    1.23
    nen
    1.22
    Activations Density 0.149%

    No Known Activations