© 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 EvalsExportsAPI 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. 10642
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direct involvement or impact

    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
    21
    +0.11
    0.6%
    294
    +0.11
    0.6%
    275
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.11
    0.02
    275
    +0.11
    0.01
    289
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.42
    ¥
    -1.70
    µ
    -1.62
    ®
    -1.56
    Īĺ
    -1.54
    £
    -1.52
    Į
    -1.52
    practice
    -1.51
     plenty
    -1.51
    wealth
    -1.48
    POSITIVE LOGITS
     proportional
    1.88
     therefrom
    1.61
     addressed
    1.58
     from
    1.58
     into
    1.56
     related
    1.56
     attributable
    1.55
     contradicts
    1.55
     accountable
    1.53
     opposite
    1.50
    Activations Density 0.182%

    No Known Activations