© 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 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. 30486
    Prev
    Next
    INDEX
    Explanations

    references to login or authentication processes

    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
    478
    +0.15
    0.9%
    156
    +0.14
    0.8%
    381
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.15
    0.11
    269
    +0.14
    0.08
    438
    +0.13
    0.06
    Negative Logits
    ³
    -1.98
    ļ
    -1.93
    µ
    -1.90
    ¿
    -1.87
    ł
    -1.84
    ¿½
    -1.82
    ¤
    -1.79
    Ľ
    -1.75
    «
    -1.74
    ij
    -1.73
    POSITIVE LOGITS
     default
    1.65
    ]{};
    1.57
    1.54
    ?:
    1.42
     unequal
    1.37
    1.36
     cry
    1.32
    ?'
    1.31
     perturbation
    1.29
     births
    1.29
    Activations Density 0.635%

    No Known Activations