© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14877
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or code structure

    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
    307
    +0.33
    2.0%
    156
    +0.25
    1.5%
    271
    +0.16
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.33
    0.09
    181
    +0.25
    0.14
    213
    +0.16
    0.09
    Negative Logits
    III
    -1.55
    ELY
    -1.49
     yet
    -1.47
     Conf
    -1.46
     LP
    -1.45
     Depression
    -1.37
     financially
    -1.36
     Hospit
    -1.35
     Basketball
    -1.32
     superiority
    -1.31
    POSITIVE LOGITS
    Ļª
    6.53
    µ
    5.66
    ĭ
    5.50
    Ń
    5.49
    ĻĤ
    5.48
    ¢
    5.47
    ±
    5.42
    ħ
    5.41
    č↵č↵
    5.38
    ↵
    5.38
    Activations Density 2.093%

    No Known Activations