© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 24368
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with chemical reactions and compositions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    271
    +0.14
    0.7%
    47
    +0.13
    0.7%
    275
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.14
    0.05
    136
    +0.13
    -0.02
    194
    +0.11
    0.03
    Negative Logits
    ontal
    -1.74
     internet
    -1.63
    idas
    -1.63
    ivent
    -1.63
     monitor
    -1.58
     awareness
    -1.49
    lando
    -1.49
     smartphone
    -1.48
     videot
    -1.48
    lymp
    -1.47
    POSITIVE LOGITS
    »¿
    1.97
    ĥ
    1.90
    Ŀ
    1.83
    Ī
    1.83
    ľ
    1.81
     hydrolysis
    1.78
    ī
    1.77
    IJ
    1.77
    ¤
    1.76
     solubility
    1.75
    Activations Density 0.570%

    No Known Activations