© 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. 9312
    Prev
    Next
    INDEX
    Explanations

    words related to newness or recent occurrences

    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
    192
    +0.14
    0.8%
    310
    +0.13
    0.7%
    99
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.14
    0.00
    404
    +0.13
    0.01
    99
    +0.11
    0.02
    Negative Logits
    ways
    -2.06
    way
    -1.66
    istics
    -1.58
    ometer
    -1.47
    ogue
    -1.47
    imetric
    -1.46
    against
    -1.45
     GOOGLE
    -1.44
    gorithms
    -1.44
    esar
    -1.44
    POSITIVE LOGITS
     onset
    2.18
    birth
    2.14
    born
    2.09
    onset
    2.03
     born
    2.00
     victims
    1.93
     birth
    1.88
     births
    1.87
     discharge
    1.80
     spontaneously
    1.79
    Activations Density 0.278%

    No Known Activations