© 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. 12392
    Prev
    Next
    INDEX
    Explanations

    references to specific types of documents or evidence for academic or legal processes

    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
    293
    +0.15
    0.9%
    17
    +0.15
    0.9%
    83
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    510
    +0.15
    0.21
    274
    +0.15
    0.20
    244
    +0.15
    0.16
    Negative Logits
    visiae
    -1.69
    unnumbered
    -1.57
    .^[@
    -1.52
    __.
    -1.41
    artifactId
    -1.36
    _."
    -1.35
    ^.
    -1.34
    soever
    -1.33
    ocamp
    -1.32
    orum
    -1.31
    POSITIVE LOGITS
    ®
    2.58
    ²
    2.56
    ľĵ
    2.47
    ĨĴ
    2.46
    Į
    2.42
    ©
    2.36
    ¼
    2.34
    ĺ
    2.30
    »
    2.29
    Ī
    2.23
    Activations Density 9.938%

    No Known Activations