© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    mentions of events and notable occurrences related to performances or cultural milestones

    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
    +0.36
    2.3%
    156
    +0.22
    1.4%
    306
    +0.22
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.36
    0.07
    306
    +0.22
    0.04
    478
    +0.22
    0.02
    Negative Logits
    ously
    -1.94
    ======
    -1.77
    nier
    -1.47
    ous
    -1.39
    zone
    -1.39
    (%
    -1.36
    gid
    -1.35
    wy
    -1.35
    eful
    -1.33
    :#
    -1.33
    POSITIVE LOGITS
     Essays
    1.51
     FITNESS
    1.27
     why
    1.27
     Just
    1.26
     how
    1.25
    feat
    1.24
     recent
    1.19
     Creating
    1.19
    proving
    1.19
     Everything
    1.19
    Activations Density 0.417%

    No Known Activations