© 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. 11442
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific details or emphasis within a text

    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
    +0.19
    1.1%
    21
    +0.15
    0.9%
    64
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.19
    0.01
    15
    +0.15
    0.02
    175
    +0.13
    0.01
    Negative Logits
    Ģ
    -1.88
    Ħ
    -1.81
    ľĵ
    -1.79
    »
    -1.77
    º
    -1.63
    ĥ
    -1.63
    own
    -1.61
    laughs
    -1.59
    Īĺ
    -1.56
    ģ
    -1.56
    POSITIVE LOGITS
     embodiments
    2.64
     disclosed
    1.76
     hereinafter
    1.72
     embodiment
    1.72
     relates
    1.70
     hereby
    1.68
     it
    1.64
     herein
    1.63
     exemplary
    1.56
     invention
    1.53
    Activations Density 0.035%

    No Known Activations