© 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. 9484
    Prev
    Next
    INDEX
    Explanations

    phrases describing the features and qualities of products

    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
    307
    +0.14
    0.8%
    466
    +0.12
    0.7%
    348
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.14
    0.13
    289
    +0.12
    0.07
    23
    +0.12
    0.10
    Negative Logits
    -4.46
    ↵
    -4.46
    -4.46
          ↵
    -4.46
    ↵↵
    -4.46
    -4.46
    -4.46
    ↵↵
    -4.46
    č↵
    -4.46
    ↵
    -4.46
    POSITIVE LOGITS
     yours
    2.49
     designed
    2.20
     compatible
    2.14
     suitable
    2.13
     fantastic
    2.10
     amazing
    2.09
     excellent
    2.08
     available
    2.05
     composed
    2.03
     hers
    2.03
    Activations Density 0.755%

    No Known Activations