© 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. 9060
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and factors related to numbers

    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
    466
    +0.23
    1.6%
    348
    +0.23
    1.6%
    78
    +0.17
    1.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.23
    0.02
    78
    +0.23
    0.00
    290
    +0.17
    0.02
    Negative Logits
    *\
    -1.32
    ↵↵
    -1.29
    ::
    -1.28
    \\
    -1.26
    ulator
    -1.24
    merce
    -1.23
    ![
    -1.22
    ité
    -1.22
    ![**
    -1.22
    wolf
    -1.22
    POSITIVE LOGITS
    ↵
    4.92
          ↵
    4.92
     ↵
    4.92
    4.92
    <|outofrange|>
    4.92
    <|outofrange|>
    4.92
    ↵
    4.92
    <|outofrange|>
    4.92
    č↵
    4.92
     ↵
    4.92
    Activations Density 0.079%

    No Known Activations