© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    numerical data and financial indicators

    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
    +0.59
    8.8%
    397
    +0.13
    1.9%
    78
    +0.12
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.59
    0.49
    397
    +0.13
    0.29
    255
    +0.12
    -0.02
    Negative Logits
    iors
    -1.17
    itals
    -1.12
    »¿
    -1.11
     respect
    -1.10
    ĸ´
    -1.07
     familiar
    -1.05
     kindly
    -1.03
     followed
    -1.03
    Ļª
    -1.02
     favour
    -1.01
    POSITIVE LOGITS
    castle
    1.06
    iston
    1.04
    thereum
    1.04
    ermo
    0.98
     crime
    0.96
     commune
    0.95
     undercover
    0.92
     transgender
    0.91
    inger
    0.91
    nutrients
    0.91
    Activations Density 14.545%

    No Known Activations