© 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. 12508
    Prev
    Next
    INDEX
    Explanations

    sequences related to programming and software development concepts

    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
    31
    +0.19
    1.1%
    243
    +0.17
    1.0%
    459
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.19
    0.17
    31
    +0.17
    0.17
    252
    +0.14
    0.12
    Negative Logits
    \]](
    -1.90
    ).](
    -1.57
     respectively
    -1.55
    cket
    -1.45
    ![
    -1.43
    ](
    -1.41
     <
    -1.37
    roc
    -1.37
    vel
    -1.36
    tics
    -1.34
    POSITIVE LOGITS
     objection
    1.52
    theless
    1.45
    iscus
    1.41
     reality
    1.39
    elson
    1.34
    fulness
    1.33
     purpose
    1.31
    mapsto
    1.31
    behind
    1.30
     causation
    1.30
    Activations Density 5.197%

    No Known Activations