© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28481
    Prev
    Next
    INDEX
    Explanations

    medical terms associated with diagnostics and assessments in clinical studies

    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
    240
    +0.20
    1.2%
    419
    +0.14
    0.8%
    17
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.20
    0.01
    82
    +0.14
    0.06
    47
    +0.13
    0.10
    Negative Logits
    named
    -1.38
     Âĵ
    -1.34
    gnu
    -1.34
    obox
    -1.33
    ``
    -1.32
     document
    -1.32
    ercase
    -1.32
    bug
    -1.31
     git
    -1.31
    raid
    -1.31
    POSITIVE LOGITS
     respectively
    2.02
     simultaneously
    1.96
     alike
    1.79
     covariates
    1.74
     coefficients
    1.74
    hee
    1.68
     rates
    1.64
     inversely
    1.61
     evenly
    1.60
    itud
    1.58
    Activations Density 1.379%

    No Known Activations