© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11607
    Prev
    Next
    INDEX
    Explanations

    terms related to signal processing and transmission

    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
    443
    +0.12
    0.7%
    354
    +0.12
    0.7%
    437
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.12
    0.02
    164
    +0.12
    0.03
    354
    +0.12
    0.02
    Negative Logits
    idenote
    -1.66
    amel
    -1.65
    ental
    -1.51
    CHAPTER
    -1.49
    TRODUCTION
    -1.45
     CURIAM
    -1.43
    olis
    -1.38
     responsibility
    -1.37
    rake
    -1.35
    ustainable
    -1.34
    POSITIVE LOGITS
     transduction
    2.87
     transducer
    2.65
     emitted
    2.19
    wave
    2.15
    boxes
    2.14
     transmitted
    2.07
     intensity
    2.06
    box
    2.03
     amplification
    2.02
     generator
    2.00
    Activations Density 0.135%

    No Known Activations