© 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. 13044
    Prev
    Next
    INDEX
    Explanations

    keywords related to communication systems and their functionalities

    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
    451
    +0.13
    0.7%
    298
    +0.12
    0.7%
    204
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.13
    0.02
    373
    +0.12
    0.03
    298
    +0.12
    0.02
    Negative Logits
    ¼
    -4.03
    ½
    -3.84
    »¿
    -3.79
    ¹
    -3.76
    ·¸
    -3.70
    č↵
    -3.67
    ↵
    -3.67
    -3.67
    <|outofrange|>
    -3.67
    ↵↵
    -3.67
    POSITIVE LOGITS
     channels
    2.73
     networks
    2.56
     between
    2.34
     channel
    2.24
     network
    2.17
     systems
    2.16
     devices
    2.15
     infrastructure
    2.15
     Networks
    2.15
     bandwidth
    2.11
    Activations Density 0.184%

    No Known Activations