© 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. 9296
    Prev
    Next
    INDEX
    Explanations

    references to assistance and experiences related to specific qualifications and benefits within a community or organization

    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
    156
    +0.15
    0.8%
    104
    +0.12
    0.7%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.15
    0.13
    291
    +0.12
    0.09
    98
    +0.11
    0.04
    Negative Logits
    naments
    -1.47
    unction
    -1.46
    quilibrium
    -1.45
    uclear
    -1.41
    dash
    -1.40
    oplasty
    -1.39
    forth
    -1.38
    dated
    -1.38
    ovember
    -1.35
    culate
    -1.35
    POSITIVE LOGITS
     professionals
    3.00
     enthusiasts
    2.83
     practitioners
    2.79
     engineers
    2.76
     investigators
    2.71
     researchers
    2.70
     managers
    2.62
     stakeholders
    2.61
     scientists
    2.58
     developers
    2.58
    Activations Density 2.898%

    No Known Activations