© 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. 11381
    Prev
    Next
    INDEX
    Explanations

    terminology related to finite and infinite concepts in mathematics

    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
    156
    +0.21
    1.2%
    118
    +0.14
    0.8%
    299
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.21
    0.01
    375
    +0.14
    0.01
    501
    +0.13
    0.01
    Negative Logits
    inson
    -1.90
    ophore
    -1.67
    éri
    -1.57
    ney
    -1.55
    iddell
    -1.47
    ère
    -1.45
    drew
    -1.42
    neys
    -1.40
    bage
    -1.40
    npm
    -1.40
    POSITIVE LOGITS
    ļ
    1.90
    ¿½
    1.86
    ĸ
    1.78
     possessions
    1.76
    »¿
    1.72
     amount
    1.70
    Ļ
    1.68
    ī
    1.68
    ·¸
    1.67
    Ĵ
    1.66
    Activations Density 0.128%

    No Known Activations