© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate methods and processes related to inventions or technical applications

    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
    306
    +0.17
    1.0%
    307
    +0.12
    0.7%
    38
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.17
    0.02
    119
    +0.12
    0.02
    428
    +0.12
    0.02
    Negative Logits
    hint
    -1.69
    icus
    -1.64
    ativity
    -1.53
    Reviewer
    -1.52
    finals
    -1.51
    LICENSE
    -1.50
    interest
    -1.49
    imeter
    -1.48
    esan
    -1.48
     hints
    -1.47
    POSITIVE LOGITS
     distributing
    2.71
     storing
    2.59
     detecting
    2.45
     obtaining
    2.44
     transferring
    2.43
     transmitting
    2.35
     treating
    2.35
     introducing
    2.33
     conducting
    2.31
     communicating
    2.29
    Activations Density 0.121%

    No Known Activations