© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    patterns involving special characters and symbols in text, particularly in programming or markup contexts

    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
    129
    +0.19
    1.1%
    410
    +0.13
    0.7%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.19
    0.01
    29
    +0.13
    0.01
    53
    +0.13
    0.05
    Negative Logits
    ian
    -1.73
    onet
    -1.64
    otte
    -1.58
    ome
    -1.55
    abouts
    -1.54
    izumab
    -1.52
    arius
    -1.52
    acle
    -1.50
    izen
    -1.49
    ario
    -1.48
    POSITIVE LOGITS
    ĻĤ
    3.62
    ł
    3.50
    Ģ
    3.44
    ↵
    3.37
    ↵
    3.37
    ↵
    3.37
    ↵
    3.37
    ↵
    3.37
    3.37
    ↵
    3.37
    Activations Density 0.504%

    No Known Activations