© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 14932
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the status or nature of software or programs

    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
    +0.15
    0.9%
    447
    +0.13
    0.8%
    300
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.15
    0.02
    167
    +0.13
    0.02
    450
    +0.13
    0.01
    Negative Logits
    ongs
    -1.76
    aters
    -1.64
    pile
    -1.45
    rij
    -1.39
    ushes
    -1.37
    aine
    -1.35
    raine
    -1.33
    ninger
    -1.32
    mathrsfs
    -1.32
     aisle
    -1.32
    POSITIVE LOGITS
     distributed
    1.93
     GPL
    1.86
     licensed
    1.62
     Copyright
    1.60
    Copyright
    1.57
     trademarks
    1.49
    distributed
    1.48
     copyrighted
    1.46
    Software
    1.45
    www
    1.44
    Activations Density 0.040%

    No Known Activations