© 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. 4-RES-SM
    11. 9860
    Prev
    Next
    INDEX
    Explanations

    terms related to kitchen appliances and their functionalities

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    306
    +0.27
    1.6%
    21
    +0.19
    1.1%
    307
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.27
    0.06
    450
    +0.19
    0.03
    36
    +0.17
    0.07
    Negative Logits
    <|outofrange|>
    -3.81
                ↵
    -3.81
    <|outofrange|>
    -3.81
    -3.81
    -3.81
    -3.81
    ↵↵
    -3.81
    č↵
    -3.81
       ↵
    -3.81
    -3.81
    POSITIVE LOGITS
    =========
    1.91
    ===========
    1.75
    ========
    1.73
    throws
    1.73
    Copyright
    1.68
    blogger
    1.64
    Category
    1.64
    Topic
    1.64
    mozilla
    1.61
    =======
    1.60
    Activations Density 0.428%

    No Known Activations