© 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. 14697
    Prev
    Next
    INDEX
    Explanations

    titles and descriptions of documents

    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
    156
    +0.22
    1.3%
    172
    +0.14
    0.8%
    27
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.22
    0.05
    90
    +0.14
    0.04
    461
    +0.13
    0.04
    Negative Logits
    orna
    -1.92
    artan
    -1.68
    )',
    -1.55
    ERE
    -1.40
    iÄĩ
    -1.39
    ANCE
    -1.39
    eston
    -1.38
    ');
    -1.38
    linger
    -1.37
    cess
    -1.36
    POSITIVE LOGITS
    keywords
    2.29
    ---
    2.25
    title
    2.14
     topic
    1.86
    tags
    1.83
    description
    1.77
     keywords
    1.74
    sidebar
    1.62
    ```
    1.60
     agenda
    1.56
    Activations Density 0.371%

    No Known Activations