© 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. 1-RES-SM
    11. 28454
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and recognition of support

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    478
    +0.14
    0.8%
    186
    +0.11
    0.6%
    208
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.11
    369
    +0.11
    0.07
    454
    +0.11
    0.10
    Negative Logits
     aside
    -1.75
    )?
    -1.70
    ).
    -1.59
    )',
    -1.58
    )</
    -1.57
    entially
    -1.56
    igraphy
    -1.55
    urally
    -1.55
    ifically
    -1.55
     {%
    -1.53
    POSITIVE LOGITS
    ]{.
    1.70
     rat
    1.50
    ez
    1.49
    č↵
    1.46
    1.46
    1.46
    1.46
    1.46
    ↵
    1.46
    ↵
    1.46
    Activations Density 1.416%

    No Known Activations