© 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. 12908
    Prev
    Next
    INDEX
    Explanations

    text related to technology and user experiences, particularly focusing on issues and solutions

    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
    +0.33
    2.0%
    21
    +0.14
    0.8%
    17
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.33
    0.03
    436
    +0.14
    0.02
    159
    +0.14
    0.06
    Negative Logits
    uality
    -1.80
     homology
    -1.68
     yourselves
    -1.64
    chitz
    -1.58
     coefficients
    -1.55
     covari
    -1.54
    dorff
    -1.53
     approximations
    -1.50
    geometric
    -1.48
     cohomology
    -1.47
    POSITIVE LOGITS
     firefox
    2.16
     login
    2.07
    ĨĴ
    2.06
    ľĵ
    2.06
     ubuntu
    1.95
    ĻĤ
    1.86
     notify
    1.82
     server
    1.80
     phone
    1.79
     wifi
    1.75
    Activations Density 0.933%

    No Known Activations