© 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. 2-RES-SM
    11. 10644
    Prev
    Next
    INDEX
    Explanations

    Java package imports and their associated classes used in a Spring framework context, particularly for data and service configurations

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    231
    +0.20
    1.1%
    315
    +0.12
    0.7%
    417
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.20
    0.06
    345
    +0.12
    0.05
    370
    +0.12
    0.06
    Negative Logits
    ).](
    -1.48
     surplus
    -1.35
    uvant
    -1.34
    .](
    -1.34
    curs
    -1.34
    cluding
    -1.33
     recurrence
    -1.33
     enlarg
    -1.30
    ).$$
    -1.30
     practice
    -1.30
    POSITIVE LOGITS
    oster
    1.71
    ģ
    1.63
    bian
    1.55
    shire
    1.53
    artifactId
    1.52
    jee
    1.52
    tools
    1.51
     chef
    1.51
    patcher
    1.51
    strap
    1.45
    Activations Density 0.341%

    No Known Activations