© 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. 9846
    Prev
    Next
    INDEX
    Explanations

    alphanumeric characters and various symbols in a string or document

    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
    9
    +0.17
    1.0%
    478
    +0.16
    0.9%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.17
    0.15
    9
    +0.16
    0.10
    500
    +0.12
    0.10
    Negative Logits
     components
    -1.55
     views
    -1.54
     versus
    -1.54
     finds
    -1.53
     entities
    -1.53
     transparency
    -1.52
     entity
    -1.51
     Figures
    -1.51
     exploration
    -1.51
     recommends
    -1.50
    POSITIVE LOGITS
    ĥ½
    6.43
    ¿½
    6.00
    »¿
    5.81
    «
    5.50
    ŀ
    5.41
    Ļª
    5.37
    ¬
    5.37
    ½
    5.16
    Į
    5.10
    ®
    5.09
    Activations Density 4.138%

    No Known Activations