© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28459
    Prev
    Next
    INDEX
    Explanations

    phrases related to stability and instability in systems

    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
    218
    +0.13
    0.7%
    497
    +0.12
    0.7%
    83
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.13
    0.06
    220
    +0.12
    0.04
    416
    +0.12
    0.04
    Negative Logits
    tons
    -1.97
    ery
    -1.83
    vas
    -1.74
    insulin
    -1.70
    burn
    -1.65
    ridges
    -1.65
    inched
    -1.61
    ibular
    -1.60
    pere
    -1.57
    cre
    -1.56
    POSITIVE LOGITS
    Ĥ¬
    2.81
    ¹
    2.59
    º
    2.49
    ¶
    2.49
    ĨĴ
    2.49
    °
    2.44
    Īĺ
    2.43
    IJ
    2.42
    ¿
    2.32
    ©
    2.31
    Activations Density 1.192%

    No Known Activations