© 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. 13010
    Prev
    Next
    INDEX
    Explanations

    technical jargon and concepts related to digital signal processing and communication methods

    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
    136
    +0.17
    0.9%
    267
    +0.13
    0.7%
    423
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.17
    0.04
    267
    +0.13
    0.05
    441
    +0.11
    -0.04
    Negative Logits
    �
    -2.88
    âĢ¯
    -2.73
    .''
    -2.73
     \'
    -2.42
    ,''
    -2.41
     ''
    -2.33
     -
    -2.31
    .."
    -2.18
    ''
    -2.18
     ..
    -2.13
    POSITIVE LOGITS
    âĢIJ
    6.67
    —
    5.82
     _
    5.73
    )—
    5.39
     _(
    4.84
    —"
    4.75
    "—
    4.60
     **_
    4.54
     _"
    4.51
    *âĢIJ
    4.50
    Activations Density 3.099%

    No Known Activations