© 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. 1-RES-SM
    11. 27955
    Prev
    Next
    INDEX
    Explanations

    terms related to systematic processes or methodologies

    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
    156
    +0.18
    1.0%
    376
    +0.15
    0.8%
    336
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.18
    0.01
    336
    +0.15
    0.01
    111
    +0.12
    0.01
    Negative Logits
     mismo
    -2.04
     specific
    -1.57
     particular
    -1.51
    aceae
    -1.49
     present
    -1.47
    iju
    -1.45
    ricanes
    -1.42
    inois
    -1.39
     actual
    -1.36
    že
    -1.34
    POSITIVE LOGITS
    °
    2.08
    "}](#
    1.79
    ¢
    1.65
    Īĺ
    1.53
    eller
    1.48
    ement
    1.46
    tee
    1.46
    ĻĤ
    1.45
    Ń
    1.45
    ķ
    1.44
    Activations Density 0.074%

    No Known Activations